mcp-a2a-documentation
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": 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 |
|---|---|
| search_documentationC | Search A2A (Agent2Agent) protocol documentation by keyword query. |
| read_documentationA | Read the full content of a specific A2A protocol documentation page. |
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
The two tools have clearly distinct purposes: search_documentation finds pages by keyword, while read_documentation retrieves a specific page's full content. There is no meaningful overlap that would cause an agent to select the wrong tool.
Both names follow a consistent snake_case verb_noun pattern: search_documentation and read_documentation. The naming is predictable and directly reflects each tool's action and target.
Two tools is a very thin surface, even for a focused documentation server. Search plus read covers the core flow, but the set feels minimal and could benefit from at least an index/listing operation.
Search and read cover the essential documentation workflow: discover relevant pages, then read full content. A listing or table-of-contents tool would improve browsing, but the current surface is workable for most agent needs.