MCP Server Example
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 |
|---|---|
| get_docsA | Search the latest docs for a given query and library. Supports langchain, openai, and llama-index. Args: query: The query to search for (e.g. "Chroma DB") library: The library to search in (e.g. "langchain") Returns: Text from the docs |
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 a single tool in the set, there is no possibility of confusing it with another tool. Its purpose (searching library documentation by query and library name) is clearly stated.
The lone name get_docs follows a clean verb_noun snake_case convention. No inconsistency is possible within a one-tool surface, though it's worth noting 'get' is slightly at odds with the described search behavior.
A single search tool is very thin for a docs-lookup server; agents have no way to list supported libraries or fetch a specific document. One tool earns its place but the surface feels under-scoped rather than well-scoped.
Only a query-based search exists, with no listing of available libraries, no fetch-by-id/page retrieval, and no error or fallback path. Notable gaps will force agents to rely on trial-and-error query strings to reach specific content.