truth-gate
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --facts | Yes | Path to the facts file the server checks documents against. The facts file is fixed when the server starts (e.g. `uv run truth-gate serve --facts /path/to/facts.yaml`); the MCP tools accept document text only, never a path. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Check a draft against the facts file before showing it to a person. Every number must come from a fact and be used in that fact's context; only listed skills may be claimed; blocked phrases fail. Fix every error and check again; warnings are style advice.
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_documentA | Check a draft (Markdown or plain text, at most 200,000 characters) against the facts file. Returns passed, error and warning counts, findings with line/column and message, and a trace from each accepted number to the fact that supports it. A longer document is rejected with an error instead of being checked in part. |
| list_factsC | The facts, skills and blocked phrases the checker uses. |
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 2 tools
check_document and list_facts are clearly distinct: one validates a draft against the facts file, the other returns the reference data the checker uses. There is no plausible way for an agent to confuse the two.
Both names follow the same snake_case verb_noun convention (check_document, list_facts). The pattern is predictable and consistent.
Two tools is thin for a fact-checking server; the surface is just 'validate' plus 'read the rules'. The narrow scope keeps it coherent, but the count sits at the borderline flagged by the rubric.
The core workflow (check a draft, inspect the facts/skills/blocked phrases) is covered, but there is no way to add, update, or validate facts through the server, and documents over 200k characters have no chunked or partial fallback. These are notable gaps that would force agents to work around the toolset.