expert-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXPERT_URL | Yes | URL of the expert-service instance | |
| EXPERT_API_KEY | Yes | API key for authentication | |
| EXPERT_PROJECT | Yes | Default project name |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| deep_searchA | Search beliefs and source documents with IDF-ranked results. No LLM call, sub-second response. This is the recommended search tool. It runs dual-path retrieval across the belief network and source document chunks, returning pre-ranked context ready for synthesis. Use this instead of calling search + list_beliefs + get_entry separately. Args: query: The question or search terms project: Project name or UUID (uses default if empty) |
| askA | Ask a question and get an LLM-synthesized answer grounded in the knowledge base. Uses the server's LLM to synthesize an answer from beliefs and source documents. Slower than deep_search but returns a ready-to-use answer. Args: question: The question to ask project: Project name or UUID (uses default if empty) |
| searchB | Full-text search across beliefs, entries, and source documents. Returns matching beliefs (with IN/OUT truth values), entry titles, and source chunk snippets. Args: query: Search terms project: Project name or UUID (uses default if empty) |
| explain_beliefA | Explain why a belief is IN or OUT by tracing its justification chain. Shows what supports this belief, what assumptions it rests on, and what would change if it were retracted. Args: node_id: The belief ID to explain project: Project name or UUID (uses default if empty) |
| what_ifA | Simulate retracting or asserting a belief without modifying the database. Shows the cascade: which beliefs would go OUT (retract) or come back IN (assert). Use this to understand the impact of changing a belief. Args: node_id: The belief ID to simulate action: "retract" or "assert" project: Project name or UUID (uses default if empty) |
| get_beliefA | Get full details for a specific belief including justifications and dependents. Args: node_id: The belief ID project: Project name or UUID (uses default if empty) |
| list_beliefsB | List beliefs in the knowledge base. Args: status: Filter by truth value -- "IN", "OUT", or empty for all project: Project name or UUID (uses default if empty) |
| list_projectsA | List all available expert knowledge bases with belief, entry, and source counts. |
| list_entriesB | List analysis entries (reports, findings, assessments). Args: topic: Filter by topic slug, or empty for all entries project: Project name or UUID (uses default if empty) |
| get_entryA | Read the full content of an analysis entry. Args: entry_id: The entry ID project: Project name or UUID (uses default if empty) |
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 10 tools
Most tools are clearly distinct, but 'ask' and 'deep_search' both involve answering questions, though their descriptions clarify different use cases. Slight overlap is mitigated by clear purpose statements.
Names predominantly follow verb_noun pattern with underscores (e.g., explain_belief, list_entries). Exceptions like 'ask' and 'what_if' are idiomatic but not disruptive.
10 tools cover the core operations for a knowledge base server: searching, retrieving, listing, explaining, and simulating. The count is well-scoped without redundancy.
The tool surface covers querying and simulation comprehensively, but lacks tools for creating or updating beliefs/entries. This may be intentional for a read-only expert server, hence a minor gap.