// SCAN REPORT

Codetree

23 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated:

1 can modify or destroy data
22 read-only
23 tools total

Community server · catalogue entry verified 11/06/2026

How to control Codetree ↓

TOOL MAP

Read (22) Write / Execute (1) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk
Write · Medium resolve_symbol resolve_symbol

1 of Codetree's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL CODETREE

PolicyLayer is an MCP gateway — it sits between your AI agents and Codetree, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations
{
  "resolve_symbol": {
    "limits": [
      {
        "counter": "resolve_symbol_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_dataflow": {
    "limits": [
      {
        "counter": "analyze_dataflow_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Codetree — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON CODETREE →

Free to start. No card required.

ALL 23 CODETREE TOOLS

WRITE 1 tools
Write resolve_symbol resolve_symbol
READ 22 tools
Read analyze_dataflow analyze_dataflow Read detect_clones detect_clones Read find_dead_code Find symbols that are defined but never referenced elsewhere in the repo. Read find_hot_paths find_hot_paths Read find_references Find all usages of a symbol across the entire repo. Read find_tests find_tests Read get_blast_radius get_blast_radius Read get_call_graph get_call_graph Read get_change_impact get_change_impact Read get_complexity Get cyclomatic complexity of a function. Read get_dependency_graph get_dependency_graph Read get_file_skeleton get_file_skeleton Read get_imports Get import/use statements from a source file. Read get_repository_map get_repository_map Read get_skeletons Get skeletons for multiple files in one call. Read get_symbol Get the full source code of a specific function or class by name. Read get_symbols Get the full source code of multiple symbols in one call. Read git_history git_history Read index_status Report on graph index freshness and stats. Read search_graph search_graph Read search_symbols search_symbols Read suggest_docs Find undocumented functions and assemble context for writing docs.

FAQ

How do I prevent bulk modifications through Codetree? +

The Codetree server has 1 write tools including resolve_symbol. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Codetree.

How many tools does the Codetree MCP server expose? +

23 tools across 2 categories: Read, Write. 22 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Codetree? +

Register the Codetree MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Codetree tool call.

Deterministic rules across all 23 Codetree tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CODETREE →

Free to start. No card required.

23 Codetree tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.