Repository navigation
📌 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):
Include all of these in your request:
Check before you post (read the values from the registry, not from memory): Check whether you're already listed on GitHub's side: Community notes from this thread. Corrections welcome. Original question (Oct 2025): 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: 155 comments 9 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 ( |
Onboarding request:
|
| 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.
|
Hi! Requesting onboarding of BoardMark to the GitHub MCP registry. Official MCP Registry name: ai.boardmark/boardmark (domain-verified, version 1.0.26) Thanks! |
|
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
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"
doneAn unauthenticated
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. |
Onboarding request: io.github.ricciflow-api/soldfetchPlease consider SoldFetch for the GitHub MCP Registry. The server is already published in the official MCP Registry.
SoldFetch provides three tools: Authenticated MCP initialization and discovery have been verified against the production endpoint, with all three tools returned. We understand that first-time inclusion is manually curated and would appreciate consideration. |
Onboarding request: nl.fermat360/fermat-360Requesting onboarding of Fermat 360 to the GitHub MCP Registry.
Fermat 360 answers questions about Dutch law from Dutch case law, legislation and EU law, with numbered citations that link to the source documents. Verify: An unauthenticated POST to https://fermat360.nl/mcp returns 401 with |
|
Request to onboard io.github.DenRakEiw/scumble (Scumble, a free, open-source desktop editor for AI inpainting; agents get 113 tools: select by text, inpaint into layers, masks, filters, PSD/ORA export).
|
Onboarding request:
|
| Field | Value |
|---|---|
| Registry name | io.github.ayeshLK/archsmith |
| Current version | 0.8.1 |
| Official registry | https://registry.modelcontextprotocol.io/?q=io.github.ayeshLK%2Farchsmith |
| Package | @archsmith/mcp-server |
| Transport | Local stdio |
| Install command | npx -y @archsmith/mcp-server |
| Repository | https://github.com/ayeshLK/archsmith |
| Server documentation | https://github.com/ayeshLK/archsmith/tree/main/packages/mcp-server |
| npm package | https://www.npmjs.com/package/@archsmith/mcp-server |
| License | Apache-2.0 |
| Credentials | None |
ArchSmith is a deterministic architecture-diagram renderer. Its MCP server lets agents read the live schema and governed registries, validate diagram IR, and render SVG without embedding an LLM or exposing per-diagram styling controls.
It exposes the get_schema, render, validate, list_registries, and get_registry tools, along with schema, registry, and rendered-diagram resources.
Verification:
- The Official MCP Registry record is active and marked as the latest version.
- A search of
https://api.mcp.github.com/v0.1/servers?search=archsmithcurrently returns zero results, so this is not a duplicate. - The server is exercised through a real MCP client in its automated test suite and requires no environment variables or external credentials.
Onboarding request:
|
| Field | Value |
|---|---|
| Registry name | io.github.sequico/server-noonien |
| Current version | 1.0.1 |
| Official registry | https://registry.modelcontextprotocol.io/?q=io.github.sequico%2Fserver-noonien |
| Package | server-noonien (npm) |
| Transport | Local stdio |
| Install command | npx -y server-noonien |
| Repository | https://github.com/sequico/server-noonien |
| License | MPL-2.0 |
| Credentials | None |
server-noonien is shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph. It exposes the same nine tools as @modelcontextprotocol/server-memory (create_entities, create_relations, add_observations, delete_entities, delete_observations, delete_relations, read_graph, search_nodes, open_nodes) plus the memory://knowledge-graph resource, and converges per-node shards across machines — over a shared folder, an S3-compatible bucket, or peer to peer with no shared area at all (the companion nooniend daemon).
Verification:
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.sequico/server-noonien"→status: active,isLatest: true, version1.0.1.
Thanks!
Onboarding request:
|
| Field | Value |
|---|---|
| Registry name | io.agentpixel/agentpixel (domain-verified namespace on agentpixel.io) |
| Version | 0.1.1, active, isLatest: true |
| Transport | Remote, Streamable HTTP: https://agentpixel.io/mcp |
| Auth | OAuth 2.1 with PKCE (S256) and dynamic client registration, or the account API key as Authorization: Bearer. Signup tools need no credential. |
| Repository | https://github.com/byron-allsourcedata/agentpixel-mcp |
| License | MIT for the repository; the hosted service is proprietary |
| Docs | https://agentpixel.io/connect |
| Privacy / terms | https://allsourcedata.io/privacy / https://allsourcedata.io/terms |
| Support | joey@allsourcedata.io |
What it does: a consent-first website pixel for agents. Visitors accept "identify this visit" before any identification runs; the agent starts a 30-day trial (no card), installs the tag, configures the consent bar, verifies installation and reads consented contacts. All 12 tools carry a title and readOnlyHint/destructiveHint annotations, plus output schemas.
Verification:
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.agentpixel/agentpixel"
Publisher: AllSource Data Corporation. Disclosure: I am the CEO. A synthetic evaluation account is available for review on request.
Onboarding request:
|
| Field | Value |
|---|---|
| Registry name | io.github.PranavNagrecha/salesforce-intelligence (GitHub namespace) |
| Version | 0.4.0, active, isLatest: true |
| Package / transport | npm sf-intelligence, local stdio: npx -y sf-intelligence mcp --vault /absolute/path/to/org-kb (or set SFI_VAULT) |
| Auth | None. Runs locally against retrieved org metadata; no API keys, no Salesforce login at query time |
| Try it without a Salesforce org | npx -y sf-intelligence demo (bundled synthetic org) |
| Repository | https://github.com/PranavNagrecha/Salesforce-Intelligence |
| Manifest | https://github.com/PranavNagrecha/Salesforce-Intelligence/blob/main/packages/cli/server.json |
| Website / docs | https://sfi.auditforce.cloud |
| License | MIT with Commons Clause (source-available) |
What it does: Ask your AI what breaks before you change Salesforce. Offline, read-only, cited answers: questions like "can I delete this field?" or "what runs when an Opportunity is saved?" are answered from the org's retrieved metadata, with citations. Not affiliated with Salesforce.
Verification
curl "https://registry.modelcontextprotocol.io/v0/servers?search=salesforce-intelligence"
Not yet listed on GitHub's side: curl "https://api.mcp.github.com/v0.1/servers?search=salesforce-intelligence" returns total: 0.
Thanks!
Onboarding request:
|
| Field | Value |
|---|---|
| Official registry name | io.github.feimacode/open-design |
| Latest version | 0.2.0 (active, isLatest), published 2026-10-10 |
| Package / transport | npm @feimacode/open-design-agent-kit-mcp 0.2.0, stdio (npx -y @feimacode/open-design-agent-kit-mcp) |
| Auth | None. Optional OPEN_DESIGN_FIGMA_TOKEN (secret) only for importing Figma frames |
| Repository | https://github.com/feimacode/open-design-agent-kit (server in packages/mcp-server) |
| Manifest | server.json |
| License | MIT |
What it does
A design library and workflow for coding agents: 163 skills, 114 design templates, 152 brand design systems and 167 remixable examples. Ask the agent for a deck, landing page, dashboard or prototype and it writes real HTML files into the project, then checks and exports them (PNG, PDF, PowerPoint, MP4/GIF, standalone HTML) through the server's 23 tools.
The server never calls a model and needs no account or API key: the agent's own model does the generation, and the server supplies the library and the bookkeeping. It uses the client's MCP roots to find the workspace, so it writes into the open folder when installed from the VS Code @mcp gallery.
Verification
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.feimacode/open-design"
Thanks for considering it.
Onboarding request:
|
| Field | Value |
|---|---|
| Registry name | io.github.SokolskyNikita/annas-mcp |
| Version | 0.2.0, active, isLatest: true |
| Package and transport | npm annas-mcp, stdio |
| Repository | https://github.com/SokolskyNikita/annas-mcp |
| License | MIT |
| What it does | Searches Anna's Archive for books and journal articles by title, author or DOI, and downloads the file the user picks. It uses the user's own Anna's Archive membership and runs locally with no telemetry. |
Verification:
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.SokolskyNikita/annas-mcp"
Onboarding request: net.softhills/mcpHello GitHub MCP Registry team, We would like to request onboarding of the official Softhills MCP server to the GitHub MCP Registry so developers can discover and install it through the VS Code MCP Gallery. The server is already published in the official MCP Registry.
Description: Official MCP server for Softhills 3D/2D Visualization SDKs, API documentation, and code examples. The server exposes 12 tools, all declared read-only, for searching and retrieving SDK documentation, API references, code examples, changelogs, and migration guides. This is a proprietary service developed and operated by Softhills. Access to the MCP service is free of charge; this does not imply an open-source license for the server or Softhills SDKs. Official Registry entry: https://registry.modelcontextprotocol.io/v0.1/servers/net.softhills%2Fmcp/versions/1.1.0 Registry verification: curl -sS "https://registry.modelcontextprotocol.io/v0.1/servers?search=net.softhills%2Fmcp" Please consider onboarding Softhills to the GitHub MCP Registry. We would be happy to provide any additional information needed for review. Thank you. |
Onboarding request:
|
| Field | Value |
|---|---|
| Registry name | com.blawgy/blawgy (domain-verified namespace) |
| Version | 1.0.0, active, isLatest: true |
| Deployment | Remote only, Streamable HTTP |
| Endpoint | https://app.blawgy.com/mcp |
| Auth | OAuth 2.1 with dynamic client registration and PKCE (RFC 9728 protected resource metadata served on 401), or a Blawgy API key as a bearer token |
| Repository | https://github.com/adamgusky/blawgy-mcp |
| License | MIT |
| Website | https://blawgy.com/mcp |
| Icon | https://blawgy.com/favicon-512.png |
What it does. Blawgy is a done-for-you SEO content service. The MCP server lets an agent read Search Console traffic, rankings and indexing, run keyword research, manage the content plan, and write, update and publish blog posts to WordPress, Shopify, Webflow, Wix, Framer, Ghost and Duda. 166 tools; destructive ones ask for confirmation. Included on every paid Blawgy plan.
Verification
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=blawgy"
{"servers":[{"server":{"name":"com.blawgy/blawgy","title":"Blawgy","version":"1.0.0","websiteUrl":"https://blawgy.com/mcp","repository":{"url":"https://github.com/adamgusky/blawgy-mcp","source":"github"},"remotes":[{"type":"streamable-http","url":"https://app.blawgy.com/mcp"}]},"_meta":{"io.modelcontextprotocol.registry/official":{"status":"active","isLatest":true,"publishedAt":"2026-10-11T03:33:13Z"}}}],"metadata":{"count":1}}Not yet on GitHub's side: curl "https://api.mcp.github.com/v0.1/servers?search=blawgy" returns no results.
Thanks for considering it.
Onboarding request:
|
| Field | Value |
|---|---|
| Registry name | ai.bankrolled/agent-hub (domain-verified, bankrolled.ai) |
| Version | 1.3.0, active, isLatest: true |
| Deployment | Remote only, Streamable HTTP |
| Endpoint | https://bankrolled.ai/mcp |
| Auth | None |
| Repository | https://github.com/Bankrolled/bankrolled-ai-docs (documentation; the hosted service is not open source) |
| License | CC BY 4.0 for the documentation repository; the hosted service is proprietary |
| Docs | https://bankrolled.ai/llms.txt |
| Server card | https://bankrolled.ai/.well-known/mcp/server-card.json |
| Icon | https://bankrolled.ai/wp-content/uploads/2026/08/cropped-mark-cropped-192x192.jpg |
| Contact | agents@bankrolled.com |
What it does. Free, sourced money facts for the US, UK, Canada, Australia and New Zealand. Four tools, all free: health_check, pricing_list (catalog and supported queries), money_fact (deposit-protection limits plus ISA, 401(k), Roth IRA and TFSA limits) and scheme_lookup (deposit-insurance scheme by country). Every answer carries the official source, an as-of date and a bankrolled.com citation.
Verification
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=ai.bankrolled/agent-hub"
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…