Wolfe-Jam

mcp-context-card

Community Wolfe-Jam
Updated

MCP server that makes a project's context (AGENTS.md), memory, and identity discoverable to any MCP client — via the Server Card _meta block and ai-catalog.json

mcp-context-card

npmCIlicense: MIT

Get one. Or add it to yours. The essential MCP server for a project'scontext, memory, and identity — discoverable to any MCP client, andrendered as one card you can read.

Light Dark
the context card, light theme the context card, dark theme

context — the project's AGENTS.md, served whole or one section at a time.

the card's context section — AGENTS.md, section nav, read_agents_md

memory — facts that persist across sessions, in a file.

the card's memory section — a real, tagged, verified fact

identity — what this server is, from its own Server Card.

the card's identity — name and pills

Discovery goes through two surfaces already in the ecosystem: the Server Card_meta block and ai-catalog.json sibling entries.

Pick one

You want to…
Add an AGENTS.md — you don't have one author_agents_md drafts one from your repo's real facts
Improve an AGENTS.md — you have one, make it the best it can be the same tool, automatically — drop in a project.faf and it upgrades to BEST: goal, who it's for, why
Get a new MCP server base — context, memory, identity, wired stand this up as-is; a host has all three before you write a tool of your own
Improve your MCP with context, memory, ID — you already run one run it alongside your existing server; nothing to migrate, it composes

A base MCP — or an extension for any other

Context, memory, and identity are essential — every MCP host needs an agentthat knows a project's instructions, remembers facts across sessions, and cansay what it is. mcp-context-card is those three, done once:

  • Stand it up as your base MCP. Point a host at it and an agent alreadyhas AGENTS.md served section‑by‑section, remember / recall / forgetmemory that survives a restart, and a whoami identity — before a singletool of your own is written.
  • Or extend any existing MCP with it. Run it alongside a server youalready have — filesystem, git, a database, your own — and that agentgains context, memory, and identity discovery it didn't have. Nothing tomigrate; it composes.

Nine tools, two discovery surfaces already in the ecosystem (Server Card_meta, ai-catalog.json), and a rendered card. MIT, on npm.

It composes:

  • serve · discover · render — this server
  • author BETTER, keep trueagents-md-facts (author_agents_md wraps it for the facts layer; adds a BEST layer of its own from project.faf when one exists)
  • files · shell · gitserver-filesystem, server-git / github‑mcp‑server, your test runner's MCP

Vendor-free — context is plain Markdown (AGENTS.md); the memory andidentity formats are swappable examples. It reads and writes only its ownthree files (AGENTS.md, project.fafm, .well-known/fafa) — no generalfile access, no shell, no search.

The card

The screenshot at the top of this page is exactly this — the same threesources rendered as one self‑contained HTML page: identity, AGENTS.md,memory, and how a machine fetches it. The view for people: read it, screenshotit, drop it in a PR, put it on a status page.

AGENTS.md sections are collapsed by default, so the card scans in one screen;a sticky index jumps to any section, Expand all opens everything. Sectionstoggle natively — the one small inline script only adds the bulk button and theprint handler. --expanded / ?expand=all renders it fully open, script-free,for a screenshot.

npx mcp-context-card card            # at a terminal: writes context-card.html and opens it
npx mcp-context-card card --expanded # every section open
npx mcp-context-card card > x.html   # piped/redirected: raw HTML to stdout
GET /card                            # live, on the HTTP transport
GET /card?expand=all&theme=light&accent=%230066cc

Light, dark, or auto; the accent defaults to the AAIF palette and takes any hex.This repo's own card, live: auto ·light ·dark(all in the AAIF accent shown here — pass any hex to change it).

Add it to your setup

No AGENTS.md yet?

The author_agents_md tool authors one — BETTER from your repo's realfacts (build/test commands, entry points, toolchain conventions, viaagents-md-facts), orBEST when a project.faf exists: the same facts, plus its structuredgoal, who it's for, and why, as a section ahead of them. Nothing toconfigure — the tier follows what's actually there.(The ladder this follows.)

To author or keep the facts layer true outside a session:

npx agents-md-facts          # author / refresh AGENTS.md
npx agents-md-facts --check  # fail if missing or stale (CI, pre-commit)

See the card

One command, no host, no config — from your project directory:

npx mcp-context-card card

At a terminal it writes context-card.html and opens it in your browser. Pipedor redirected (> card.html, a script, CI) it writes raw HTML to stdout instead;--stdout forces that from a terminal too. --expanded opens every section.

Wire it into a host

Claude Desktop, Cursor, or any stdio host:

{
  "mcpServers": {
    "context-card": {
      "command": "npx",
      "args": ["-y", "mcp-context-card"],
      "env": { "MCP_CONTEXT_CARD_ROOT": "/abs/path/to/your/project" }
    }
  }
}

MCP_CONTEXT_CARD_ROOT points at the directory with your AGENTS.md. Thememory tools work with or without it; identity is optional. Over HTTP instead:PORT=8080 npx mcp-context-card. Requires Node ≥20.

If command: "npx" fails to spawn (spawn npx ENOENT — seen on Cursor, whosehost process doesn't inherit a shell PATH), point command at node andthe installed dist/bin.js instead — seedocs/WIRING.md. Transport choice isin docs/TRANSPORT.md.

Extending an MCP you already run: most hosts accept more than onemcpServers entry — add context-card alongside server-filesystem,server-git, or your own, and every agent in that host gains context,memory, and identity discovery without anything else changing.

Why

AGENTS.md is the de-facto standard for telling a coding agent how to work in arepo. But a client has to know the file exists and read the whole thing intocontext. There is no standard way for a server to say "here is my AGENTS.md,here is what I remember, here is who I am" — so every server that wants thisgrows its own shape.

mcp-context-card answers all three through mechanisms that already exist:

  1. Server Card _meta (SEP‑2127) —one reverse‑DNS‑namespaced key per concern, readable in‑band as an MCPresource and at GET /.well-known/mcp/server-card.
  2. ai-catalog.json — sibling entries keyed by media type, atGET /.well-known/ai-catalog.json.

The context concern points at AGENTS.md (text/markdown). Memory and identityhave no de‑facto standard yet, so the examples here use.fafm and.fafa — one instantiation each,swap in your own.

The wire‑level detail is in docs/MECHANISMS.md.

Tools

Tool What it's for
author_agents_md draft an AGENTS.md — BETTER from the repo's facts (via agents-md-facts), BEST when a project.faf exists — ready to drop in
read_agents_md return the project's AGENTS.md — whole, or one section by heading
list_agents_md_sections the headings, so a client pulls one section instead of the whole file
remember write a fact that will still be there next session
recall read a fact stored in a previous session
forget drop or correct a stale fact
whoami this server's name, vendor, version, status, license
list_context_sources what this project publishes, in what media types, via which surface
render_context_card the whole card as one self‑contained HTML page (also GET /card)

The demo

npm run demo runs every tool over both transports:

  1. Context — list the AGENTS.md sections, then pull just ## Test.
  2. Memoryremember() a fact, stop the server process, start a new one,recall() the same fact. Only the file carries it across.
  3. Identitywhoami(), and the Server Card _meta block read back from alive client.
  4. Discoverylist_context_sources(), then the same server over statelessHTTP with its .well-known routes and GET /card.

104 tests on Linux, macOS, and Windows, coverage‑gated in CI. Two spawn a realchild process and check a remembered fact survives the restart — one againstan existing project.fafm, one starting from a project that has never hadone; another checks the stdio and HTTP tool surfaces match.

Layout

Path What
src/server.ts the nine tools + the Server Card resource
src/agents-md.ts reads and section‑splits AGENTS.md
src/author.ts author_agents_md — BETTER via agents-md-facts, BEST when project.faf exists
src/md.ts a minimal dependency‑free Markdown → HTML renderer
src/render-card.ts the card — identity + AGENTS.md + memory + discovery, as one HTML page
src/memory.ts file‑backed remember / recall / forget
src/identity.ts whoami (.fafapackage.json fallback) + the _meta block
src/catalog-gen.ts writes ai-catalog.json from the same three sources
src/transport/http.ts the stateless Streamable HTTP app (Hono)
src/bin.ts the entry point — stdio · --http · card · --help · --version

Related

License

MIT.

This repo dogfoods what it serves — its AGENTS.md is a real, current file, andit ships a project.faf as the structured source behind it.

MCP Server · Populars

MCP Server · New

    irinabuht12-oss

    Google Ads MCP + Meta Ads MCP + GA4 — one unified MCP server

    Google Ads MCP + Meta Ads MCP + GA4 in one server for Claude, ChatGPT, Cursor & n8n — 250+ tools, hosted remote MCP, OAuth login, no API keys. By Ryze AI.

    Community irinabuht12-oss
    irinabuht12-oss

    Google Ads MCP Server

    Google Ads MCP + Meta Ads MCP + GA4 in one server for Claude, ChatGPT, Cursor & n8n — 250+ tools, hosted remote MCP, OAuth login, no API keys. By Ryze AI.

    Community irinabuht12-oss
    irinabuht12-oss

    Meta Ads MCP Server (Facebook and Instagram Ads)

    Google Ads MCP + Meta Ads MCP + GA4 in one server for Claude, ChatGPT, Cursor & n8n — 250+ tools, hosted remote MCP, OAuth login, no API keys. By Ryze AI.

    Community irinabuht12-oss
    aicanvas-me

    @aicanvas/mcp

    Open-core registry of animated React components, blocks, design systems, and templates. Real, editable code: install with one shadcn CLI command or let your AI agent pull it over MCP.

    Community aicanvas-me
    aicanvas-me

    AI Canvas

    Open-core registry of animated React components, blocks, design systems, and templates. Real, editable code: install with one shadcn CLI command or let your AI agent pull it over MCP.

    Community aicanvas-me