MCP Server Published But Not Visible on github.com/mcp Registry

[Wolfe-Jam]

📌 Update, Oct 2026: how onboarding works (community notes)

This thread became the place to request listing on github.com/mcp. These notes collect what's been said here.

The process (based on the accepted answer, @trent-j, May 2026):

1. Publish to the open-source MCP Registry first. Your entry should be active and isLatest.
2. Request onboarding here. Adding a new server to github.com/mcp is a manual curation step.
3. After that, new versions sync automatically from the open-source registry. No need to ask again for updates.

Include all of these in your request:

• Registry name (e.g. io.github.you/server or a domain-verified namespace), linked to its registry entry
• Version, active + isLatest
• Package and transport (npm / PyPI / cargo, stdio), or the remote endpoint and auth (streamable HTTP, OAuth / API key)
• Repository
• License
• What it does, in one or two lines
• Verification: the registry curl below, so the values can be checked

Check before you post (read the values from the registry, not from memory):

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=<your-server>"

Check whether you're already listed on GitHub's side:

curl "https://api.mcp.github.com/v0.1/servers?search=<your-server>"

_{Community notes from this thread. Corrections welcome.}

---

Original question (Oct 2025):

Hi community! Looking for clarification on how the GitHub MCP Registry works.
The Situation
We successfully published claude-faf-mcp to GitHub's MCP Registry (Anthropic-approved steward), but it's not appearing on github.com/mcp yet. We're curious about the process.
Quick Details

Server: claude-faf-mcp
Namespace: io.github.Wolfe-Jam
GitHub: https://github.com/Wolfe-Jam/claude-faf-mcp
npm: https://npmjs.com/package/claude-faf-mcp (3,600+ downloads, 800+ weekly)
Status: Published successfully (v2.6.1 via CLI)
Credentials: Official Anthropic MCP steward (PR #2759 merged)

Questions

Is github.com/mcp a curated list (vs automatic sync)?
If curated, what are the selection criteria?
How do we check publication status?
Any feedback on what might help visibility?

Why We Ask
claude-faf-mcp is the first persistent "Project DNA" layer in MCP — helps developers standardize AI context across teams. Visibility on github.com/mcp would help the ecosystem discover and adopt it.
Context

Previously posted: modelcontextprotocol/registry #690
Anthropic registry: ✅ Accepted and merged
Looking for guidance from anyone familiar with the curation process

Thanks for any insights! 🙏

[ghost]

39 days, no response.

claude-faf-mcp is approved by Anthropic (PR #2759 MERGED), has 10,067+ npm downloads, but isn't visible on github.com/mcp despite being listed in modelcontextprotocol/servers.

What are the curation criteria for github.com/mcp? Is there a separate approval process beyond the Anthropic PR?

Links:

• https://github.com/Wolfe-Jam/claude-faf-mcp
• Add claude-faf-mcp to MCP servers registry modelcontextprotocol/servers#2759

[ghost]

🎉 Update: Additional Milestone Since Posting

.faf is now IANA-registered as application/vnd.faf+yaml

This makes claude-faf-mcp:

• Built on an official Internet-standard format
• Only persistent project context MCP server with IANA-registered
  foundation
• Increased long-term stability and interoperability

Full details: https://www.faf.one/blog/iana-registration

Still curious about the github.com/mcp curation process and happy to
provide any additional info that might help.

[hstaudacher]

Hey @Wolfe-Jam,
right now the GitHub MCP registry is a curated list. This will change in a couple days when we enable sync with the open source registry. In order to get your server added, you have to publish it to the open source registry first. Here is a guide how to publish your server if you haven't done it already.

[ghost]

Hey HolgerMany thanks for your reply, we will take of it and let you know. thanks again,James (Wolfe) HarrisonFounderWolfe James LLCfaf.one - Project DNA for AI contextIANA Registered format .FAF for AI context application/vnd.faf+yaml"README evolution for AI era"Google Gemini CLI(9.5/10 Rating)  On Nov 10 2025, at 8:52 am, Holger Staudacher ***@***.***> wrote: Hey @Wolfe-Jam, right now the GitHub MCP registry is a curated list. This will change in a couple days when we enable sync with the open source registry. In order to get your server added, you have to publish it to the open source registry first. Here is a guide how to publish your server if you haven't done it already. —Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: ***@***.***>

[Wolfe-Jam]

Hey @hstaudacher - following up from November.

Just published both FAF packages to the open source registry today:

• io.github.Wolfe-Jam/claude-faf-mcp v3.3.7
• io.github.Wolfe-Jam/faf-mcp v1.2.1

Ready for sync whenever that goes live.

If there's anything blocking the registry sync rollout, happy to help test, validate, or contribute. We've been through the mcp-publisher flow and can provide feedback if useful.

[Wolfe-Jam]

Hey @hstaudacher — friendly follow-up from the November conversation about registry sync.

Quick update on where things stand: we now have 6 FAF MCP servers published to the open source registry, all passing mcp-registry-validator with zero schema and zero lint issues:

Server	Registry	Schema	Lint
claude-faf-mcp	npm + MCP	0	0
faf-mcp	npm + MCP	0	0
grok-faf-mcp	npm + MCP	0	0
gemini-faf-mcp	PyPI + MCP	0	0
rust-faf-mcp	npm + MCP	0	0
wjttc	npm + MCP	0	0

All published via mcp-publisher, all on 2025-12-11 schema, all under namespace io.github.Wolfe-Jam.

You mentioned back in November that github.com/mcp would start syncing from the open source registry. Is that sync live now? If so, is there something on our end we need to do to appear? If it's still in progress, totally understand — just want to make sure we're not missing a step.

Happy to help test or validate anything on the sync pipeline.

[Wolfe-Jam]

Status check, 2026-05-18: github.com/mcp still shows ~97 servers, so the open-source-registry sync doesn't look live yet. The FAF servers remain published & schema-clean on the OSS registry.

If the list stays curated long-term: grok-faf-mcp is a distinct candidate on its own merit — the first MCP server for Grok, URL-based (zero install), just shipped v1.3.1 and registry-coherent. Flagging it specifically, not asking for blanket inclusion.

Is there an ETA for the sync, or is github.com/mcp staying curated? Either answer's fine — closing the loop on this thread.

[trent-j]

Hi @Wolfe-Jam, thanks for the thoughtful follow-up and for continuing to publish and validate your servers.

A few clarifications from our side: the GitHub MCP Registry now has the ability to sync versions from the open source registry, but onboarding a new server is still a manual curation process today. Once a server has been onboarded, newly published versions from the OSS registry should sync from there.

I’m closer to the technical side than the product/curation criteria, so I don’t want to overstate anything here. I’ll share your request with our product team and ask whether we’re able to move forward with onboarding them.

Thanks again for your patience, and for offering to help validate the sync path.

[cx-anand-nandeshwar]

Hi @trent-j

Could you please provide the exact steps or documentation required to list or publish my custom MCP server to the GitHub Registry https://github.com/mcp registry. I have security MCP server (Org level) which is used to provide security vulnerability remediation.

I have already raise an support ticket for the process but didn't get any resolution for this. Ticket: 4444073

[Wolfe-Jam]

Hey @trent-j — thanks again for looking into this and for offering to take it to the product team, genuinely appreciate it.

Quick update from our side: since May we've moved our two flagship servers to the FAF Foundation's DNS-verified one.faf/* namespace on the OSS registry — one.faf/claude-faf-mcp and one.faf/faf-mcp (both active + latest; my solo io.github.Wolfe-Jam entries deprecated — they served their purpose). So those are the canonical names now if onboarding moves forward. We've also added copilot-instructions emit (so .faf feeds GitHub Copilot directly), and a full GitHub version is in testing.

No rush at all on the github.com/mcp side — mostly I'd love to understand the lay of the land so we can be ready: is onboarding/sync something that's moving, or staying curated for now? And if there's a process, criteria, or anything we should prep on our end to make it easy when the time comes, happy to do the legwork.

Either way — thanks for keeping the channel open. 🙏

[trent-j]

We really appreciate your interest and the effort you put into getting your servers listed on the GitHub MCP Registry. We’re glad to share that they have now been onboarded.

[Wolfe-Jam]

Wow! what amazing news, thank you for your patience and steer, much appreciated.

[Wolfe-Jam]

Thanks again, trent-j 🙏 — two more of the FAF family are now published on the official MCP registry and ready whenever onboarding has room:

• Grok FAF — one.faf/grok-faf-mcp · https://github.com/Wolfe-Jam/grok-faf-mcp
• Gemini FAF — one.faf/gemini-faf-mcp · https://github.com/Wolfe-Jam/gemini-faf-mcp

Both are live on registry.modelcontextprotocol.io under one.faf/*, following the OSS-registry-first process from this thread.

No rush at all — thanks for keeping the channel open.

[edithatogo]

Onboarding request: io.github.edithatogo/fyi-mcp

Following the process clarified in this thread (OSS registry first; github.com/mcp initial onboarding is manual curation; versions sync after onboard):

Field	Value
Official registry name	io.github.edithatogo/fyi-mcp
Latest version	0.1.2 (active / isLatest)
Repository	https://github.com/edithatogo/fyi-cli
server.json	https://github.com/edithatogo/fyi-cli/blob/master/server.json
Description	Local-first FOI/OIA request tracker MCP for Alaveteli platforms (FYI.org.nz and multi-jurisdiction catalog)

OSS registry verification

curl -sS "https://registry.modelcontextprotocol.io/v0/servers?search=fyi-mcp"

returns io.github.edithatogo/fyi-mcp v0.1.2 active/latest.

github.com/mcp status (2026-07-09)

• Search fyi-mcp / edithatogo does not surface a curated card for this server
• https://github.com/mcp/io.github.edithatogo/fyi-mcp → 404

Could the product/curation team please consider onboarding this server so OSS version sync can take effect? Happy to provide additional metadata or validation help.

Tracked in: edithatogo/fyi-cli#32

[AkashGoenka]

Onboarding request: io.github.AkashGoenka/coldstart

Following the OSS-registry-first process described in this discussion:

• Official registry name: io.github.AkashGoenka/coldstart
• Latest version: 2.2.17
• Package: @cstart/coldstart (npm, stdio)
• Repository: https://github.com/AkashGoenka/coldstart
• Website: https://coldstartmcp.dev/
• Documentation: https://coldstartmcp.dev/docs/

coldstart provides self-maintaining codebase memory for AI coding agents: an AST index for exact code navigation plus agent-written notes that flag themselves stale when code changes.

The package includes the required mcpName marker and matching server.json, and the latest version is published to the official MCP Registry.

Please consider onboarding it to the GitHub MCP Registry so future versions can sync automatically. Thank you!

[happy520ai]

Onboarding request: io.github.happy520ai/unified-ai-system

Following the OSS-registry-first and manual-curation process confirmed in this discussion:

Field	Value
Official Registry name	io.github.happy520ai/unified-ai-system
Latest version	0.4.8 (active)
Package / transport	ghcr.io/happy520ai/unified-ai-system/mcp-server:0.4.8 / stdio
Repository	https://github.com/happy520ai/unified-ai-system
Manifest	https://github.com/happy520ai/unified-ai-system/blob/master/server.json
Documentation	https://happy520ai.github.io/unified-ai-system/codex-mcp-docker-quickstart.html

Unified AI System is an Apache-2.0 self-hosted gateway that gives Codex, Cursor, Cline, and generic MCP clients nine bounded tools. Its differentiating first-run path turns rough natural-language requests into structured, reviewable prompts locally, with a deterministic fake provider and no account or API key required. Real provider calls remain explicit and disabled by default.

The repository publishes pinned OCI images and runs public CI, container, MCP discovery, security-scanner, clean-clone, and process-cleanup checks. The Official Registry currently contains versions 0.3.1 through 0.4.8; GitHub MCP search still returns no result.

Please consider onboarding this server so future Official Registry versions can sync. I am happy to provide any additional metadata or validation evidence the curation team needs.

[cpellan561]

Onboarding request: to.derive/derive

Following the OSS-registry-first process confirmed in this thread (publish to the open source registry, then request manual onboarding; versions sync after):

Field	Value
Official registry name	to.derive/derive
Latest version	1.0.0 (active, isLatest)
Transport	Remote, Streamable HTTP at https://derive.to/mcp
Auth	OAuth 2.1, PKCE (S256), Dynamic Client Registration
Repository	https://github.com/derive-to/derive
Manifest	https://github.com/derive-to/derive/blob/main/server.json
Website	https://derive.to
Licence	FSL-1.1-ALv2 (converts to Apache 2.0)

Derive gives agent output a permanent home. One call publishes a document, styled page, deck, or report to a versioned URL a teammate can open and comment on inline; the agent reads those comments back and revises. Every tool carries a title and honest readOnlyHint / destructiveHint annotations, so annotation-aware clients auto-approve the reads and prompt on the writes.

Nothing to install and no key to paste — it is a remote server behind OAuth with dynamic client registration. Self-hosting is a single container, for teams that cannot send work to a hosted service.

OSS registry verification:

curl -sS "https://registry.modelcontextprotocol.io/v0/servers?search=to.derive"

returns to.derive/derive v1.0.0, status: active, isLatest: true.

github.com/mcp status (2026-08-12): a search for derive surfaces no card, and https://github.com/mcp/to.derive/derive returns 404.

Could the curation team consider onboarding this so future OSS registry versions sync automatically? Happy to provide any further metadata or validation.

[OlyaTi]

Onboarding request for a server already published to the OSS registry, following the format used earlier in this thread.

• Registry name: io.github.mnemoverse/mcp-memory-server
• Latest version: 0.8.1 (isLatest: true)
• What it is: persistent memory for AI agents, shared across tools: write a memory in one MCP client, recall it in another. Importance-scored writes, associative recall, feedback-tuned ranking, shared memory rooms.
• Remote: https://mcp.mnemoverse.com/mcp (Streamable HTTP, OAuth 2.1 + PKCE, RFC 9728 protected-resource metadata, dynamic client registration; vscode.dev is in the DCR allowlist, and loopback callbacks work for VS Code Desktop)
• Package: npm: @mnemoverse/mcp-memory-server (stdio, API-key auth)
• Repo: https://github.com/mnemoverse/mcp-memory-server (MIT)
• Verification:
  curl "https://registry.modelcontextprotocol.io/v0/servers?search=mnemoverse" returns the entry above; an unauthenticated POST https://mcp.mnemoverse.com/mcp returns 401 with a WWW-Authenticate: Bearer challenge and a resource_metadata pointer, per spec.
• Tool annotations: all ten remote tools carry title plus readOnlyHint/destructiveHint; the two destructive delete tools are deliberately not exposed on the remote endpoint.

Happy to provide a populated test account for review. Thanks for considering.

[rafaelgaspar]

Requesting onboarding for a new server:

Field	Value
Official registry name	io.github.rafaelgaspar/longhorn-mcp
Latest version	0.1.1 (active / isLatest)
Package / transport	npm — longhorn-mcp, stdio (npx -y longhorn-mcp)
Repository	github.com/rafaelgaspar/longhorn-mcp
Manifest	server.json
Documentation	README
License	MIT
Description	MCP server for the Longhorn distributed storage manager API. Full read/write coverage of Longhorn's REST API — volumes, snapshots, backups, backing images, nodes, settings, engine images, recurring jobs, and more — plus a --read-only mode, stdio and Streamable HTTP transports, and an official Helm chart for in-cluster deployment.

OSS registry verification:

curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.rafaelgaspar/longhorn-mcp"

returns the server with "status": "active" and "isLatest": true.

Publishing is automated via GitHub Actions OIDC on every tagged release (.github/workflows/release.yaml), so future Official Registry versions should sync automatically once onboarded. Would appreciate this being added to the GitHub MCP Registry — thanks!

[Ollynov]

Onboarding request: io.github.Ollynov/ball-ranks

Requesting initial GitHub MCP Registry onboarding for Ball Ranks, following the OSS-registry-first, manual-curation process described in this thread.

Field	Value
Registry name	io.github.Ollynov/ball-ranks
Version	1.0.0, active, isLatest
Registry entry	https://registry.modelcontextprotocol.io/v0.1/servers?search=ball-ranks
Endpoint	https://ballranks.com/api/mcp (Streamable HTTP)
Auth	None for the free V0 data
Tools	4 read-only tools: weekly rankings, season rankings, player rankings, and player projections
Website	https://ballranks.com
Repository	Private repository at https://github.com/Ollynov/yosho-ball
License	Proprietary hosted service
Support	help@ballranks.com

Ball Ranks gives agents NFL and NBA fantasy rankings and player projections. It is free to connect without an account or API key.

The official registry returns the entry as active and latest, while https://api.mcp.github.com/v0.1/servers?search=ball-ranks currently returns no results. Please consider it for onboarding so future official-registry versions can sync automatically. Thank you.

[khanarmaghanrasheed-18]

Onboarding request: io.github.khanarmaghanrasheed-18/dataset-explorer

Please consider Dataset Explorer for inclusion in github.com/mcp.

Item	Details
Official MCP Registry	io.github.khanarmaghanrasheed-18/dataset-explorer
Version and status	0.2.1; active; isLatest = true (checked from the Registry API)
Package	dataset-explorer-mcp 0.2.1 on PyPI
Transport and authentication	Local stdio; no server API key required
Repository and documentation	MCP-Dataset-Explorer
License	MIT

Dataset Explorer helps your AI assistant understand files on your own computer.
Ask it to summarize data, check missing values and repeated rows, or spot unusual
patterns. It supports CSV, TSV, Excel (.xlsx and .xls), JSON, and Parquet files,
and reads them without changing them. Its ten tools run locally; no website or
Gemini API key is needed.

For relationships between columns, it uses Pearson correlation for two numeric
columns, eta squared to compare numeric values across groups, and Cramer's V for
two category columns. The method is chosen to suit the column types and calculated
from the dataset. These statistics measure association, rather than proving causes.

Installation: uvx dataset-explorer-mcp or pip install dataset-explorer-mcp.
The published package passed 14 checks, including MCP initialization, tool
discovery, and real dataset analysis through stdio in a clean installation.

Registry verification:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.khanarmaghanrasheed-18%2Fdataset-explorer"

[wheelerhubbell]

Onboarding request: io.github.wheelerhubbell/whp-standing

Field	Value
Registry name	io.github.wheelerhubbell/whp-standing
Version	1.0.4 (active, isLatest: true in the official registry)
Transport	streamable-http, https://standing-guard-service.lovable.app/mcp
Repository	https://github.com/wheelerhubbell/wheelerhubbell.github.io (client under packages/client)
Description	Provenance and authority checks, paid per call with x402 (USDC on Base).

Published to the official registry and verified there. It is not yet at https://github.com/mcp/io.github.wheelerhubbell/whp-standing. Please onboard it when you can. Thank you.

[nguyenhieuec]

Onboarding request: 3 servers in the app.openkrill namespace

Same maintainer, one comment for all 3 to keep the thread short.
All 3 are domain-verified (openkrill.app), remote only, streamable HTTP, no auth, no API key, read-only.

Registry name	Version	Remote endpoint	What it does
app.openkrill/papers	1.0.0 (active, isLatest: true)	https://papers.openkrill.app/mcp	Search Europe PMC, Crossref and arXiv, and get a paper's abstract and free full-text link from its DOI.
app.openkrill/seo-audit	1.2.0 (active, isLatest: true)	https://seoaudit.openkrill.app/mcp	Audits up to 25 pages for technical SEO problems and checks AI search readiness for a local business site.
app.openkrill/company-jobs	1.2.0 (active, isLatest: true)	https://jobs.openkrill.app/mcp	Lists open jobs from a company's public Greenhouse, Lever, Ashby, Workable or SmartRecruiters board.

• Repository: none public. These are hosted services; docs at https://tools.openkrill.app.
• License: hosted service, free to call; source is not published.
• Verification: curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=app.openkrill" (values above read from it on 2026-10-08). curl "https://api.mcp.github.com/v0.1/servers?search=openkrill" returns 0 today.

Disclosure: I maintain these servers, and a coding agent prepared this request for me.

[oaleviola]

Onboarding request: io.github.oaleviola/arroway

Following the OSS-registry-first process in this thread: the entry is published to the open-source registry and the values below were read from it today.

Field	Value
Registry name	io.github.oaleviola/arroway
Version	0.1.45 (active, isLatest: true)
Transport and auth	Remote, Streamable HTTP at https://www.arroway.app/api/mcp. OAuth: sign in the first time, nothing to paste
Repository	https://github.com/oaleviola/arroway-plugin
License	MIT (plugin repository)
Website	https://www.arroway.app

What it does: Arroway orchestrates people and AI agents around the decisions in force. Any AI connected to it reads what is currently decided before it acts, and records what it did when it finishes; a person approves what is saved.

Verification:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=arroway"

returns io.github.oaleviola/arroway 0.1.45 with status "active" and isLatest true (published 2026-10-06). On GitHub's side, https://api.mcp.github.com/v0.1/servers?search=arroway returns count 0 and a search for "arroway" on github.com/mcp finds nothing.

Could the curation team consider onboarding it, so future registry versions sync? Happy to provide anything else you need.

[bryntay]

Onboarding request: gallery.a1/a1-gallery

Please consider A1 Gallery for the GitHub MCP Registry. Values below were read from the official registry on 8 October 2026.

Field	Value
Registry name	gallery.a1/a1-gallery (DNS-verified namespace on a1.gallery)
Version	1.1.2, active, isLatest: true
Transport	Remote, Streamable HTTP: https://www.a1.gallery/api/mcp
Auth	OAuth 2.1 with PKCE and dynamic client registration. Free with an A1 account (50 calls a day), Pro 2,000 a day
Tools	17, all read-only
Repository	https://github.com/bryntay/a1-mcp (connection guide and registry metadata; the server itself is hosted)
License	MIT for the repository files; the hosted service is proprietary
Docs	https://www.a1.gallery/mcp
Privacy / terms	https://www.a1.gallery/privacy / https://www.a1.gallery/terms
Support	hello@a1.gallery

What it does: search a hand-curated gallery of 1,150+ real websites by style, font, colour, section and technology. It returns captured sections, full pages, fonts and design values measured off the live page (hex colours with roles, type sizes and weights, spacing, radius, layout). Useful as design reference when an agent builds or reviews a UI.

Verification:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=gallery.a1/a1-gallery"
curl "https://api.mcp.github.com/v0.1/servers?search=a1-gallery"   # 0 results today, not yet onboarded

Thank you.

[aaronjmars]

Onboarding request: fun.aeon/aeon

Please consider Aeon for github.com/mcp. Values below were read from the official registry on 8 October 2026.

Field	Value
Registry name	fun.aeon/aeon (DNS-verified namespace on aeon.fun)
Version	1.0.0, active, isLatest: true
Transport	Remote, Streamable HTTP: https://www.aeon.fun/connect/mcp
Auth	OAuth 2.1 with PKCE, dynamic client registration or Client ID Metadata Documents. Sign in with GitHub, then pick which Aeon agent (repo) the client may use
Repository	https://github.com/aeonfun/aeon (the framework; the MCP server itself is hosted)
License	MIT
Website	https://www.aeon.fun

What it does: Aeon is an open-source autonomous agent that runs skills on a schedule with GitHub Actions in your own repo. This server lets you drive your Aeon agent from chat: list and run skills, follow runs and read their output, search its memory, edit its strategy and voice, install skill packs and change settings. Writes are tool-annotated and commit to the user's own repo; secrets are never readable over MCP.

Verification:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=fun.aeon"

Thank you!

[dmeursing]

Onboarding request: com.fusehealth/mcp

Please consider FUSE Health for the GitHub MCP Registry. Values below were read from the official registry on 2026-10-08.

Field	Value
Registry name	com.fusehealth/mcp (DNS-verified namespace on fusehealth.com)
Version	0.1.0, active, isLatest: true
Transport	Remote, Streamable HTTP: https://mcp.fusehealth.com/mcp
Auth	OAuth 2.1 with PKCE (S256) and dynamic client registration. Sign in with a FUSE brand account, or create a free developer sandbox from the sign-in page (no card). No API key to paste.
Repository	None. Hosted, closed-source service; the registry entry is remotes-only.
License	Proprietary hosted service (terms, privacy)
Docs	https://www.fusehealth.com/developers/ai-connector
What it does	FUSE is the commerce platform for health and wellness brands. Launch offerings, set pricing, run promotions, manage your storefront and track sales by chatting with your AI. It asks before public or store-changing actions (enforced server-side), reporting is aggregate-only, and it never moves money.

Verification:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=com.fusehealth"

Publisher: FUSE Health, Inc. (support@fusehealth.com)

[MattDavies]

Onboarding request: codes.qrx/mcp

Please consider QRX for the GitHub MCP registry.

Field	Value
Registry name	codes.qrx/mcp (domain-verified)
Version	1.0.0, active, isLatest
Transport	Remote, streamable HTTP at https://qrx.codes/mcp, API key (Authorization: Bearer)
Repository	https://github.com/qrxcodes/qrx-mcp
License	MIT
What it does	Makes artistic QR codes from a link and a picture prompt, and checks each one scans before returning it.

Verification:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=codes.qrx/mcp"

Publisher: MakerX Pty Ltd (matt@makerx.com.au, hello@qrx.codes).

[waynehamadi]

Onboarding request: dev.datacircle/datacircle

Please consider Datacircle for github.com/mcp. Values below were read from the official registry on 9 October 2026.

Field	Value
Registry name	dev.datacircle/datacircle (domain namespace, verified by HTTP proof on datacircle.dev)
Version	1.0.2, active, isLatest: true (published 2026-10-09)
Transport	Remote, Streamable HTTP: https://api.datacircle.dev/mcp
Auth	OAuth 2.1: the 401's WWW-Authenticate points to the protected resource metadata, dynamic client registration, PKCE (S256). A Datacircle API key also works as Authorization: Bearer
Repository	none: a hosted server, closed source
License	proprietary hosted service; free to connect, calls paid from the user's balance (a $5 credit at sign-up)
Docs	https://docs.datacircle.dev/mcp-server
What it does	Datacircle is a data co-op. Query your favorite B2B data APIs through us. Same request, same price, no markup. Right now we have 2 live LinkedIn profile APIs that we trust: Up2Data and HarvestAPI.

Verification:

curl "https://registry.modelcontextprotocol.io/v0.1/servers/dev.datacircle%2Fdatacircle/versions/latest"

Disclosure: Datacircle is my company.

[hanria-bot]

Request: add HANRIA Mandate Check to the GitHub MCP Registry

• Registry name: ai.hanria/agent-mandate-check (namespace verified by DNS for hanria.ai)
• Version: 0.7.1, status active, isLatest true
• Transport: remote, streamable HTTP, https://check.hanria.ai/v1/mcp
• Authentication: none
• Description: Free, advisory pre-action check. check_action returns permit, deny or escalate for a proposed agent action against the operator's written mandate, with the governing clause and an Ed25519-signed receipt; validate_mandate checks a mandate for errors. Mandate templates are offered as MCP resources. Keeps no request content.
• Homepage: https://hanria.ai
• Source: hosted service; no public repository.
• Verify: curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=ai.hanria/agent-mandate-check"

[mertkayacs]

Onboarding request: io.github.mertkayacs/reevesagents

Please consider reevesagents for the GitHub MCP Registry. Values below were read from the official registry on 2026-10-09.

Field	Value
Registry name	io.github.mertkayacs/reevesagents (GitHub namespace, published from CI with GitHub OIDC)
Version	1.8.0, active
Transport	Local stdio, npm package reevesagents, started as reevesagents mcp
Auth	None
Repository	https://github.com/mertkayacs/reevesagents
License	Apache-2.0
What it does	Lets one coding agent spawn, read and steer other AI coding CLIs (Claude Code, Codex, Kimi, OpenCode and more), each in its own local tmux window.

I am the author. Thank you.

[nofait-platform-team]

Onboarding request: io.github.no-fait/infinite-audience

Please consider Infinite Audience, published by NO FAIT (dba Infinite Audience), for initial onboarding to the GitHub MCP Registry, following the registry-first, manual-curation process described in this discussion.

Infinite Audience lets AI assistants discover audiences, build segments, match customer data, and deliver data to activation channels. Some actions may incur billable usage; access is authenticated and governed by server-side scopes.

Field	Value
Official MCP Registry name	io.github.no-fait/infinite-audience
Registry entry	https://registry.modelcontextprotocol.io/v0.1/servers/io.github.no-fait%2Finfinite-audience/versions/latest
Published version	1.0.3 (active, isLatest: true)
Transport	Remote Streamable HTTP
Production endpoint	https://mcp.infiniteaudience.ai/mcp
Authentication	First-party OAuth with PKCE and Dynamic Client Registration
Product website	https://infiniteaudience.ai
Documentation and connection guide	https://docs.infiniteaudience.ai/agents/mcp/
Repository / licensing	Proprietary hosted service; implementation and publisher manifest are maintained in the private no-fait/platform repository. No public source package is required to connect.
Support	support@infiniteaudience.ai · https://infiniteaudience.ai/contact
Privacy / terms	https://nofait.ai/privacy · https://nofait.ai/terms

Publication and verification (2026-10-09): A fresh readback of the official Registry's canonical latest-version endpoint confirms version 1.0.3, status: active, and isLatest: true. The Registry reports publication on September 27, 2026. GitHub's registry API returns zero entries for infinite-audience.

curl -sS 'https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.no-fait%2Finfinite-audience'
curl -sS 'https://api.mcp.github.com/v0.1/servers?search=infinite-audience'

Could the curation team review this existing remote server for inclusion and let us know if additional public metadata or a dedicated reviewer account is required? Thank you.

[emmafar]

Hi! Requesting onboarding of BoardMark to the GitHub MCP registry.

Official MCP Registry name: ai.boardmark/boardmark (domain-verified, version 1.0.26)
Transport: remote, Streamable HTTP — https://mcp.boardmark.ai/mcp
Auth: OAuth 2.1 (DCR + Client ID Metadata Documents), or a personal access token
Repository (client configs, MIT): https://github.com/i-c-develop/boardmark
Docs: https://mcp.boardmark.ai/connect.md
What it does: issue board (issues, sprints, comments, project docs as markdown) — agents work with the signed-in user's own permissions.
Publisher: I C Develop Co., Ltd — support@boardmark.ai

Thanks!

[AminDhouib]

Requesting initial GitHub MCP Registry onboarding for the Devino Solutions servers, following the OSS-registry-first, manual-curation process described in this thread. Devino Solutions (14930398 Canada Inc., https://devino.ca) builds and runs all of them; contact hello@devino.ca.

All 14 are published and active + isLatest on the official registry (domain-verified namespaces, except upAPI which is under io.github), none appears on github.com/mcp yet (api.mcp.github.com/v0.1/servers?search=<name> returns total: 0 for each). Every server is a hosted remote over Streamable HTTP with OAuth 2.1 + PKCE and dynamic client registration; no API keys. Client configs, docs links and per-server READMEs are in one public MIT repo: https://github.com/DevinoSolutions/mcp-servers.

Registry name	Version	Transport	Remote URL	Repository	License	What it does
now.sendly/sendly	1.0.0	streamable-http	https://app.sendly.now/api/mcp	mcp-servers/sendly	MIT	Send transactional email, draft and run campaigns, build onboarding workflows, manage contacts and segments, and fix deliverability with Sendly.
io.superbooks/superbooks	1.0.0	streamable-http	https://app.superbooks.io/mcp	mcp-servers/superbooks	MIT	Work with your SuperBooks books: categorize transactions, match receipts, draft and send invoices, chase unpaid ones, and read P&L, runway and spending reports.
now.voicelabs/voicelabs	1.0.0	streamable-http	https://app.voicelabs.now/api/mcp	mcp-servers/voicelabs	MIT	Generate speech from text in your VoiceLabs voices, transcribe audio to text, and manage your voice library, including consented voice cloning.
io.notifly/notifly	1.0.0	streamable-http	https://api.notifly.io/mcp	mcp-servers/notifly	MIT	Manage Notifly notification workflows, subscribers and topics, trigger delivery across email, SMS, push, chat and in-app, and check whether a message landed.
com.usepostify/postify	1.0.0	streamable-http	https://app.usepostify.com/api/mcp	mcp-servers/postify	MIT	Draft, schedule and publish social posts to your connected LinkedIn, X, Instagram, TikTok and other channels, and read post analytics in your Postify calendar.
com.getbioflow/bioflow	1.0.0	streamable-http	https://app.getbioflow.com/api/mcp	mcp-servers/bioflow	MIT	Edit and publish your BioFlow link-in-bio page: add, reorder or remove links and blocks, go live on a schedule, and read page views, clicks and signups.
io.dodomain/mcp	1.0.0	streamable-http	https://app.dodomain.io/api/mcp	mcp-servers/dodomain	MIT	Connect your customers' custom domains to your product with doDomain: preflight a domain, start a guided DNS connect session, verify records and check health.
com.nowgetitdone/getitdone	1.0.1	streamable-http	https://app.nowgetitdone.com/api/mcp	mcp-servers/getitdone	MIT	Create, update and track tasks and projects in your GetItDone team workspaces: capture to-dos from notes, review your workload and dig into any task.
com.aishorty/shorty	1.0.0	streamable-http	https://aishorty.com/api/mcp	mcp-servers/shorty	MIT	Summarize YouTube videos, web pages, articles and documents, transcribe audio and video, add captions, and search your saved summaries with Shorty.
io.snapvisor/snapvisor	1.0.0	streamable-http	https://mcp.snapvisor.io/	mcp-servers/snapvisor	MIT	Review SnapVisor visual regression builds: see what changed in screenshot diffs, approve or reject builds, handle flaky changes and join review threads. MCP access needs a paid SnapVisor plan.
com.getuptimely/uptimely	1.0.0	streamable-http	https://app.getuptimely.com/api/mcp	mcp-servers/uptimely	MIT	Manage uptime monitors, incidents and status pages in Uptimely: check what is down, add monitors, run incident response step by step and draft postmortems.
io.github.DevinoSolutions/upapi-mcp	0.2.0	streamable-http (also npm @upapi/mcp, stdio)	https://app.upapi.io/api/mcp	mcp-servers/upapi (source: upapi-mcp)	MIT	Call a catalog of ready-to-use APIs such as web search, Wikipedia, GitHub, scraping, screenshots, PDF and OCR through one upAPI account, with no signup at each upstream service.
net.unotes/unotes	1.0.0	streamable-http	https://unotes.net/api/mcp	mcp-servers/unotes	MIT	Search a library of university course material: past exams, assignments, lab reports and lecture notes, plus your uNotes flashcards and quizzes. All tools read-only.
com.trycaly/caly	1.0.0	streamable-http	https://mcp.trycaly.com/mcp	mcp-servers/caly	MIT	Find open meeting times, book, reschedule and cancel meetings, and read your event types, bookings and working-hours schedules in Caly.

Verification. Registry values above were read from the registry today (2026-10-09), not from memory:

for n in now.sendly/sendly io.superbooks/superbooks now.voicelabs/voicelabs io.notifly/notifly \
         com.usepostify/postify com.getbioflow/bioflow io.dodomain/mcp com.nowgetitdone/getitdone \
         com.aishorty/shorty io.snapvisor/snapvisor com.getuptimely/uptimely \
         io.github.DevinoSolutions/upapi-mcp net.unotes/unotes com.trycaly/caly; do
  curl -s "https://registry.modelcontextprotocol.io/v0.1/servers?search=$n"
done

An unauthenticated initialize POST to each remote URL (Accept: application/json, text/event-stream) returns 401 with an RFC 9728 WWW-Authenticate challenge pointing at the protected-resource metadata, which is the expected response for a probe:

• app.sendly.now/api/mcp → 401, WWW-Authenticate: Bearer resource_metadata="https://app.sendly.now/.well-known/oauth-protected-resource/api/mcp"
• app.superbooks.io/mcp → 401, WWW-Authenticate: Bearer resource_metadata="https://app.superbooks.io/.well-known/oauth-protected-resource"
• app.voicelabs.now/api/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://app.voicelabs.now/.well-known/oauth-protected-resource"
• api.notifly.io/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://api.notifly.io/.well-known/oauth-protected-resource/mcp"
• app.usepostify.com/api/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://app.usepostify.com/.well-known/oauth-protected-resource"
• app.getbioflow.com/api/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://app.getbioflow.com/.well-known/oauth-protected-resource"
• app.dodomain.io/api/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://app.dodomain.io/.well-known/oauth-protected-resource"
• app.nowgetitdone.com/api/mcp → 401, WWW-Authenticate: Bearer resource_metadata="https://app.nowgetitdone.com/.well-known/oauth-protected-resource", scope="workspaces:read tasks:read tasks:write projects:read"
• aishorty.com/api/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://aishorty.com/.well-known/oauth-protected-resource"
• mcp.snapvisor.io/ → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://mcp.snapvisor.io/.well-known/oauth-protected-resource"
• app.getuptimely.com/api/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://app.getuptimely.com/.well-known/oauth-protected-resource"
• app.upapi.io/api/mcp → 401, WWW-Authenticate: Bearer resource_metadata="https://app.upapi.io/api/auth/.well-known/oauth-protected-resource"
• unotes.net/api/mcp → 401, WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://unotes.net/.well-known/oauth-protected-resource"
• mcp.trycaly.com/mcp → 401, WWW-Authenticate: Bearer resource_metadata="https://mcp.trycaly.com/.well-known/oauth-protected-resource"

Most of the apps have a free tier, so a reviewer can sign in through the OAuth flow with a fresh account; happy to provision test accounts (including a paid SnapVisor seat) or answer anything else. Thanks for curating this.