zme-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZME_MCP_TOKEN | No | Bearer token for the HTTP endpoint. ChatGPT carries it in the connector URL. Unset = unauthenticated (localhost only). | |
| NVIDIA_API_KEY | No | Enables the vector arm of hybrid search. Without it, everything still works in lexical mode (which is the arm that catches exact identifiers). | |
| ZME_SUPABASE_KEY | Yes | Supabase key for the ZME project. The anon key is enough (SELECT-only + zme_remember). Never deploy a service-role key on a shared machine. | |
| ZME_SUPABASE_URL | No | Supabase URL for the ZME project. Defaults to Zeug's own memory project. Point at another ZME deployment (e.g. a ClawPanel tenant DB) to serve that instead. |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Search Zeug's knowledge base. Returns {results: [{id, title, url}]} — call fetch(id) for full content. Natural-language questions work best. |
| fetchA | Fetch the full content of one search result by its id (a chunk UUID returned by search). |
| recallA | Recall what Zeug itself wrote down — notes, analysis, compiled research. Use this (not search) for 'why did we decide X' questions. Set wide=true to also include articles and social posts. |
| whyA | Causal chain between two entities in the knowledge graph, e.g. why('kimi CLI 0.27.0', 'loop.ts CLI_COMMANDS fix'). Use canonical names. |
| nearB | Facts around one entity in the knowledge graph, with evidence quotes. |
| rememberA | Record a durable fact — a pitfall, decision, or incident — so it survives the session. Becomes searchable after the next ingest run. Never store secrets. Requires the zme:write scope in OAuth mode. |
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 targets a distinct operation: search is for broad knowledge base lookup, recall is specifically for Zeug's own notes, near and why explore the knowledge graph from different angles (neighborhood vs. causal paths), fetch retrieves full content for search hits, and remember writes new facts. Minor overlap exists between search and recall, but the descriptions clearly partition them.
All tool names are single lowercase words, giving a clean, consistent visual style. However, the names mix verbs (search, fetch, recall, remember) with non-verbs (near, why), which slightly weakens the semantic consistency of the naming convention.
With 6 tools, the set is well-scoped for a knowledge management server. Each tool addresses a distinct need (lookup, detail retrieval, graph exploration, self-notes, causal analysis, and memory writing), with no apparent redundancy.
The main workflows are covered: searching and retrieving content, exploring entity relations, recalling internal notes, tracing causality, and recording durable facts. Missing capabilities like updating or deleting existing facts are minor and don't block primary use cases.