pydantic-docs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PDA_DATA_DIR | No | Path to data directory for search indices and JSONL files | |
| PDA_DOC_ROOT | No | Path to Pydantic v2 source documentation | |
| PDA_DOC_ROOT_AI | No | Path to Pydantic AI source documentation |
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 |
|---|---|
| health_pingA | Returns simple pong |
| health_validateB | Validate search indices and data integrity |
| pydantic_modeB | Report data roots and offline mode. |
| pydantic_searchB | Search local Pydantic + Pydantic-AI docs with filters. |
| pydantic_getA | Fetch a local doc page and return plain text + html. Supports chunking for large documents via max_chars parameter. |
| pydantic_sectionC | Extract a section by anchor from a local page. |
| pydantic_apiB | Jump to an API page by symbol name. Optional anchor. |
| admin_rebuild_indicesA | Rebuild BM25 search indices from JSONL files. Use when indices are missing or corrupted. |
| admin_cache_statusA | Get detailed status of documentation cache including file counts and sizes. |
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 9 tools
Tools are mostly distinct: admin and health tools handle backend tasks, while pydantic tools handle content retrieval. pydantic_get and pydantic_section could be confused (both fetch page content), but descriptions clarify that get returns full text and section extracts a specific anchor.
Naming follows a clear 'category_verb' pattern: admin_*, health_*, pydantic_*. Within pydantic, verb_s are used (api, get, mode, search, section). This consistency helps agents predict tool behavior.
9 tools is an appropriate size for a documentation server. It covers admin operations, health checks, and core doc retrieval/search without being too sparse or overwhelming.
The tool set covers essential doc operations: search, fetch page, extract section, jump to API. However, missing a tool to list available pages or get a table of contents, which would be useful for discovery.