anchor-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANCHOR_API_KEY | No | Optional. The API key for the hosted Project Brain. When set, the server reads real data instead of the bundled sample project. |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_brainA | Ask a question about the product's own history — decisions, constraints, what customers said — and get the fragments that bear on it, each with the source it came from. Returns 'nothing answers that' rather than guessing when the brain has not read it. |
| list_contradictionsA | Statements in the project's sources that cannot both be true, with both sides quoted and the question somebody has to answer to resolve each one. This is usually the highest-value call: contradictions are what a person cannot hold in their head across six tools. |
| list_gapsA | Questions no source answers, with the role that can answer each and what it blocks. Deliberately returns no citations — there is nothing to cite, which is the point. |
| list_sourcesA | Everything the brain has read for this project — interviews, PRDs, tickets, threads, docs — with how many fragments came out of each. Use it to see what an answer could possibly be based on before you trust one. |
| get_fragmentA | Fetch one fragment by id with its full text and where it sits in its source. Every other tool cites fragment ids; this is how you open one. |
| draftA | Draft a PRD section, user stories or acceptance criteria for a topic, with every line traced to the fragment behind it and the open questions listed underneath. Refuses to draft when no source supports the topic. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool serves a clearly distinct purpose: fetching a fragment, drafting content, querying the brain, listing contradictions, listing gaps, and listing sources. There is no functional overlap, so an agent can reliably choose the right tool based on the task.
The list_* tools are consistent, but get_fragment, draft, and ask_brain deviate from a uniform verb_noun pattern. Despite this, all names are lowercase with underscores and the verbs are descriptive, making the set readable and predictable overall.
With six tools, the server is well-scoped for its purpose of analyzing and synthesizing project sources. Each tool earns its place, and the count is within the ideal 3-15 range.
The tool set covers the main workflows: inspecting sources, retrieving fragments, querying historical context, surfacing contradictions and gaps, and drafting. A minor gap is the lack of a tool to list all fragments or ingest new sources, but the server appears intentionally read-only, so this is an acceptable limitation.