FactAnchor-MCP
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_verified_contextA | Fetch real, source-of-truth web text for a topic and wrap it in a strict fact-anchoring guardrail so the LLM answers ONLY from it. Use this tool BEFORE answering any factual question. Then answer the user strictly from the returned block and follow the embedded STRICT RULES (never guess, cite sources in brackets, do not use pre-trained knowledge for missing info). Args: query: The factual topic or question to ground. max_results: How many web sources to pull (default 3, max 5). |
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 1 tool
With only one tool, there is no possibility of confusion between tools. The single tool has a clearly distinct purpose.
The single tool name 'fetch_verified_context' follows a clear snake_case convention and is descriptive. Consistency is not an issue with only one tool.
One tool is slightly below the typical 3-15 range, but it is appropriate for this narrowly scoped server. The tool covers the entire workflow of fetching and anchoring factual context.
The single tool effectively covers the entire domain of fact-anchoring: fetching verified context and enforcing strict answer rules. No obvious gaps exist for its stated purpose.