# Taproot: AT Protocol MCP (com.atproto-mcp/taproot): tool descriptions scored

- tools/list taken: 2026-11-02 (UTC)
- From: [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.atproto-mcp%2Ftaproot/versions/latest)
- Connected to: https://mcp.atproto.at/mcp
- Homepage: https://atproto-mcp.com/
- Scoring rules: v2
- Tools: 27
- Average: 65.6 / 100 (Cloudy)
- Near-identical pairs: 0

This page shows how Taproot: AT Protocol MCP (com.atproto-mcp/taproot)'s tool descriptions scored, the issues found and the names of its tools and parameters. The descriptions are the server's own: read them where the copy came from.

Forecall asked the URL this server lists in the official MCP Registry for its tools/list once, on the date above, without calling any tool. The server may have changed since.

## Across the server

- Minor: 27 tools. Above 25, models start to tell tools apart less well.
- Minor: The server's instructions are 3503 characters. Claude Code reads only the first 2,048 by default (Codex 0.154.0 reads them whole). Put what the server is for first.

## Tools

- `get_account_history`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_latest_commit`: 52 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_did_document`: 55 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_profile`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_repo_status`: 57 / 100
  - Major: Says nothing about when to use it, or when not to.
- `list_labelers`: 57 / 100
  - Minor: No `required` list, so every argument is optional.
- `get_thread`: 60 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_app_link`: 62 / 100
- `get_pds_directory_info`: 62 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_relay_directory_info`: 62 / 100
  - Major: Says nothing about when to use it, or when not to.
- `query_labels`: 62 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_backlinks`: 67 / 100
  - Major: Says nothing about when to use it, or when not to.
- `list_blobs`: 67 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
- `resolve`: 67 / 100
  - Major: Says nothing about when to use it, or when not to.
- `list_backlink_records`: 68 / 100
  - Major: Says nothing about when to use it, or when not to.
- `list_records`: 68 / 100
  - Major: Says nothing about when to use it, or when not to.
- `get_record`: 69 / 100
- `list_repos_by_collection`: 69 / 100
  - Major: Says nothing about when to use it, or when not to.
- `verify_handle`: 69 / 100
- `describe_pds`: 70 / 100
- `search_accounts`: 70 / 100
  - Major: Says nothing about when to use it, or when not to.
  - Minor: The description mentions none of its 3 or more arguments.
- `count_repos_by_collection`: 72 / 100
  - Major: Says nothing about when to use it, or when not to.
- `resolve_lexicon`: 72 / 100
  - Major: Says nothing about when to use it, or when not to.
- `list_repos`: 75 / 100
  - Major: Says nothing about when to use it, or when not to.
- `count_records`: 77 / 100
- `get_blob_info`: 77 / 100
- `search_lexicons`: 77 / 100
  - Minor: No `required` list, so every argument is optional.

Is your server listed here and you would rather it were not? Email support@forecall.dev, and we will take it off within 7 days.

[All scored servers](https://forecall.dev/en/servers)
