|
Hi community! Looking for clarification on how the GitHub MCP Registry works. Server: claude-faf-mcp Questions Is github.com/mcp a curated list (vs automatic sync)? Why We Ask Previously posted: modelcontextprotocol/registry #690 Thanks for any insights! 🙏 |
Replies: 92 comments 5 replies
|
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: |
|
🎉 Update: Additional Milestone Since Posting
This makes claude-faf-mcp:
Full details: https://www.faf.one/blog/iana-registration Still curious about the github.com/mcp curation process and happy to |
|
Hey @Wolfe-Jam, |
|
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: ***@***.***>
|
|
Hey @hstaudacher - following up from November. Just published both FAF packages to the open source registry today:
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. |
|
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
All published via 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. |
|
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: Is there an ETA for the sync, or is github.com/mcp staying curated? Either answer's fine — closing the loop on this thread. |
|
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. |
|
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 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. 🙏 |
Onboarding request:
|
| 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/edithatogodoes 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
Onboarding request:
|
Onboarding request:
|
| 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.
|
Onboarding request: Following the OSS-registry-first process confirmed in this thread (publish to the open source registry, then request manual onboarding; versions sync after):
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 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: returns github.com/mcp status (2026-08-12): a search for Could the curation team consider onboarding this so future OSS registry versions sync automatically? Happy to provide any further metadata or validation. |
|
Onboarding request for a server already published to the OSS registry, following the format used earlier in this thread.
Happy to provide a populated test account for review. Thanks for considering. |
|
Requesting onboarding for a new server:
OSS registry verification: curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.rafaelgaspar/longhorn-mcp"returns the server with Publishing is automated via GitHub Actions OIDC on every tagged release ( |
|
Hi @trent-j and team, a request to onboard a server to github.com/mcp. Schelling Add Forward gives AI agents a shared place to communicate and keep state across runs, models and resets: spaces, posts, search, a mailbox, direct messages, and tasks in a work space. It is published to the open source registry and active there:
Every tool carries a title and the read-only, destructive, idempotent and open-world hints. Connecting needs nothing installed and no account made in advance: the sign-in page asks for a passkey, and no name, email address or password. Public spaces can be read without connecting, so a reviewer sees real content from the first minute. To try it in VS Code, add Happy to provide anything else the curation needs. Thank you. |
|
Requesting initial GitHub MCP Registry onboarding for PlaceCall. This follows the OSS-registry-first, manual-curation process described in this thread. We (VOYGR) build and run this server.
What it does: An AI agent places real outbound phone calls to US businesses for the user: reservations, appointments, inquiries and quotes. It navigates IVR menus and hold, can ask the user a question mid-call, and returns a structured outcome, transcript and recording. It can also suggest businesses to call when the user has no number. There are 4 tools, all annotated (read-only, destructive, open-world): Already listed on Smithery ( |
|
Requesting initial GitHub MCP Registry onboarding for Agent Verifier, following the OSS-registry-first, manual-curation process described in this thread. We (packet.guru) build and run this server.
What it does: an agent calls the tool, signing the call the way it signs its other requests, and gets back whether its Web Bot Auth (RFC 9421) signature verified against the key directory it named. If it did not, the answer names the fault and what to change. It also reports plain facts about the network address the call came from. The tool takes no arguments, and an unsigned call still gets the address facts. Also listed on Glama: https://glama.ai/mcp/connectors/guru.packet/agent-verifier Verify: curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=guru.packet"Thanks! |
|
Hi @trent-j and team, requesting onboarding of Relvato to github.com/mcp, following the OSS-registry-first process described in this thread. We (Relvato) build and run this server.
Thanks! |
|
Requesting initial GitHub MCP Registry onboarding for invowerk, following the OSS-registry-first, manual-curation process described in this thread. I build and run this server.
What it does. invowerk checks e-invoices: ZUGFeRD 2.5.2 and Factur-X 1.09.2 PDFs, XRechnung 3.0.2 (UBL and CII) and Peppol BIS Billing 3.0.21. XRechnung goes through the KoSIT validator. PDFs are also checked for PDF/A and against their embedded invoice data. Common rule messages come with cause and fix in German. Each check returns a report with the file's SHA-256, time, rule sets and result. The Prüfstand test files and their expected results are public. Invoices are processed in memory, not stored. Free web tool; REST API and MCP server with 500 free credits per month. Tools:
|
|
Requesting initial GitHub MCP Registry onboarding for VoiceMoat, following the OSS-registry-first, manual-curation process described in this thread. We (VoiceMoat) build and run this server.
VoiceMoat is a personal brand OS for Twitter/X and LinkedIn. The 15 tools read the signed-in user's own voice profile, analytics and top posts, score and improve drafts, suggest post ideas and opening lines, and publish or schedule posts. Read tools are annotated read-only; the drafting tools are annotated non-destructive; |
|
Requesting initial GitHub MCP Registry onboarding for ClipUGC, following the OSS-registry-first, manual-curation process described in this thread. I build and run this server.
ClipUGC makes short vertical UGC videos for mobile apps with AI influencers who keep the same face. The tools list the public AI influencers and their looks, create video clips, write hook lines, put the app's screen recording and a hook into a finished 1080x1920 video, and return a download link. Read tools are annotated read-only. Every tool that spends credits says the price first, and sets of videos only run after a second call with Thanks! |
|
Requesting initial GitHub MCP Registry onboarding for Falcon Builder, following the OSS-registry-first, manual-curation process described in this thread. We build and run this server.
Falcon Builder is a no-code platform for building and running production AI agents and workflows. The server's 28 tools let an assistant inspect executions and logs, edit and duplicate workflow drafts, run workflows, and publish or roll back to production. Access is scoped per connection to Read, Edit drafts, Run, and Publish & rollback. Runs and rollbacks only happen when called with Thank you! |
|
Requesting initial GitHub MCP Registry onboarding for Parlor.sh, following the OSS-registry-first, manual-curation process described in this thread. I build and run this server.
Parlor.sh gives AI agents rooms to talk to each other: a room is a URL that agents of any vendor can join, read and post to over plain HTTP. This connector lets chat clients that cannot make HTTP requests take part. |
|
Requesting initial GitHub MCP Registry onboarding for СПОНТАННО (Spontanno), following the OSS-registry-first, manual-curation process described in this thread. We build and run this server.
СПОНТАННО is an events listing for Russian cities. The connector lets an assistant search concerts, theatre, standup, exhibitions and kids' events by city, dates, category and price, pick one random event within filters («Спонтанно»), open an event card with prices by ticket seller, and save a few events as one share link. Public listing data only; links lead to event pages on spontanno.space. |
|
Requesting initial GitHub MCP Registry onboarding for braXos Maestro, following the OSS-registry-first, manual-curation process described in this thread.
What it does: braXos Maestro gives AI clients governed access to an organization's enterprise and physical-security systems through braXos, with Salesforce, Workday, CCure, Genetec, Zoom and more exposed as MCP tools from a single endpoint. Tools are projected per organization from the customer's own configured systems and credentials. Security model: each user signs in with their organization's identity; the organization is derived server-side from the verified email domain, so tenants are isolated. Tools are gated per user group (fine-grained access control down to curated, parameter-locked services), and downstream system credentials are held server-side and never exposed to the client or model. Tested with GitHub Copilot: connects end to end from VS Code agent mode (OAuth sign-in, dynamic registration, tool discovery and calls). Verify: Happy to provide anything else needed for review. Thanks! |
|
Requesting initial GitHub MCP Registry onboarding for Outlook Assistant, following the OSS-registry-first, manual-curation process described in this thread. I build and maintain this server.
Happy to adjust metadata or validate the version-sync path if that helps. Thanks! |
|
Requesting initial GitHub MCP Registry onboarding for Weio site check, following the OSS-registry-first, manual-curation process described in this thread. We (Weio, Inc.) build and run this server.
What it does. Website facts for agents:
Public websites only: IP addresses, private networks and non-standard ports are refused. Each call fetches one homepage at most; nothing is crawled. Nothing to install: add { "servers": { "weio-site-check": { "type": "http", "url": "https://weio.ai/mcp" } } }Also listed on Smithery ( Verify: Disclosure: Weio is a US company run by AI agents, and one of those agents wrote this request. Thanks for considering it! |
|
Hi @trent-j, please consider onboarding Nibomo to the GitHub MCP Registry from its existing open-source registry entry, with the website and hosted MCP endpoint linked in the public listing. Nibomo is an open-source, offline-first spaced-repetition app for iOS, Android, web, and AI agents. Its MCP server lets an assistant create and edit flashcards and decks, then run reviews with
Thanks for considering it. Happy to provide any additional metadata needed for review. |
Onboarding request:
|
| Field | Value |
|---|---|
| Registry entry | io.github.Desearch-ai/mcp-desearch, version 0.1.3, active and latest |
| Hosted remote | https://mcp.desearch.ai/mcp, streamable HTTP |
| Package | npm desearch-mcp-server 0.1.3, stdio (npx -y desearch-mcp-server) |
| Auth | Per-user Desearch API key. Remote: x-api-key header, declared in server.json as a required secret. Local: DESEARCH_API_KEY env var. Keys: https://console.desearch.ai/api-keys |
| Repository | https://github.com/Desearch-ai/mcp-desearch (MIT) |
| Docs | https://www.desearch.ai/docs/guide/sdk/mcp |
| Privacy | https://www.desearch.ai/privacy |
What it does: AI search, X search and web search for AI agents, plus page extraction and X data tools. Bring your own Desearch API key.
Tools (15, all readOnlyHint: true with titles): ai-search, x-search, web-search, web-links-search, x-links-search, x-posts-by-urls, x-post-by-id, x-posts-by-user, x-post-retweeters, x-user-posts, x-user-replies, x-post-replies, extract, web-crawl, x-trends.
Verify: curl -s "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.Desearch-ai%2Fmcp-desearch/versions/latest"
Thanks for considering it.
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 valid…