mcp-context-card
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_agents_mdA | Return this project's AGENTS.md — the whole file, or one section by heading. The instructions a client would otherwise have to know to look for and read wholesale. |
| author_agents_mdA | Author an AGENTS.md for this project and return the draft — BETTER from repo facts alone (via agents-md-facts: real build/test commands, entry points, toolchain conventions, nothing invented), or BEST when a project.faf exists (facts plus its structured goal/who/why as a second managed block ahead of them). Does not write a file. |
| list_agents_md_sectionsA | List the headings in this project's AGENTS.md, so a client can pull one section instead of spending context on the whole file. |
| rememberA | Persist a fact past the session boundary — written to a .fafm file, not held in memory. Reusing an existing id replaces that fact's text in place (no duplicate); a new id appends. Facts are written verification_status: unverified. |
| recallA | Retrieve a fact stored in a previous session by id. Exact lookup — not fuzzy or substring. |
| forgetA | Remove a fact by id — to correct or drop something stale. A missing id is reported, not an error. |
| whoamiA | This server's own identity — name, vendor, version, status, license — from its .fafa card. |
| list_context_sourcesA | What context does this project publish (AGENTS.md, memory, identity), in what media types, and through which discovery surface. For a client connecting cold. |
| render_context_cardA | Render the project's business card as one self-contained HTML page a person can read or screenshot. Front: name, title, one-liner. Flip it for the back: About, Skills (when the .fafa lists any), Context (AGENTS.md), Memory, Discovery. layout:"portrait" for the tall view; expanded:true renders both faces flat with every section open. Also served at GET /card (?expand=all) over the HTTP transport. |
| save_context_cardA | Write the context card to context-card.html in the project and, when this server runs locally, open it in the person's browser. Returns the card as Markdown (identity, AGENTS.md sections, memory, discovery) plus a clickable link to the saved file. Use this instead of pasting render_context_card's HTML into a chat that can't display it. Replaces any earlier context-card.html. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Server Card | This server's identity + the _meta context block. |
| Context Card | The context card as an MCP App: identity, AGENTS.md, memory and discovery, rendered inline by hosts that support MCP Apps. |
TDQS
Scored across 10 tools
Most tools have distinct resource+action targets (author/read/list AGENTS.md, remember/recall/forget facts, whoami vs list_context_sources). The clearest overlap is save_context_card vs render_context_card, both about the context card, though descriptions clarify one renders to HTML and one saves a file. whoami and list_context_sources also touch identity/discovery but remain distinguishable.
Six tools follow a clean verb_noun snake_case pattern (author_agents_md, list_agents_md_sections, list_context_sources, read_agents_md, save_context_card, render_context_card). The remaining four (forget, recall, remember, whoami) break that pattern into bare verbs/nouns. Mixed conventions but still readable and unambiguous.
Ten tools is well within the ideal 3-15 range and each maps to a distinct capability (AGENTS.md authoring/reading, memory CRUD, card rendering/saving, identity, discovery). No tool feels redundant or padded.
Memory lifecycle (remember/recall/forget, with remember handling in-place updates) and card rendering/saving are complete. AGENTS.md has author/read/list-sections but author_agents_md only drafts and never writes a file, leaving a minor gap in the AGENTS.md write path that a client must work around.