// SCAN REPORT

code-intel MCP Server

30 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

2 can modify or destroy data

28 read-only

30 tools total

Community server · catalogue entry verified 03/07/2026

How to control code-intel MCP Server ↓

TOOL MAP

What code-intel MCP Server exposes to your agents

Read (28) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous code-intel MCP Server tools

Execute · High query The tool explicitly executes queries against a graph database/codebase. Execute · High raw_query This tool executes user-supplied query strings against a graph backend.

2 of code-intel MCP Server's 30 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control code-intel MCP Server

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

Cap read operations

{
  "blast_radius": {
    "limits": [
      {
        "counter": "blast_radius_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register code-intel MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CODE-INTEL →

Instant setup, no code required.

FULL CATALOGUE

All 30 code-intel MCP Server tools

EXECUTE 2 tools

Execute query Execute a GQL (Graph Query Language) query. Supports FIND, TRAVERSE, PATH, and COUNT. More expressive than raw Execute raw_query Execute a simplified Cypher-like graph query. Supports: name=\

READ 28 tools

Read blast_radius Impact analysis: traverse the call/import graph to find all symbols that depend on or are affected by a given Read cluster_summary Rich summary of a module/cluster: purpose, key symbols, dependencies, health Read clusters List detected code clusters (directory-based communities) with member counts and top 10 symbols each. Useful f Read complexity_hotspots Ranked list of functions/methods by cyclomatic complexity. Useful for identifying refactoring candidates. Read coverage_gaps Find exported symbols with no test coverage, ranked by blast radius. Useful for prioritizing test writing. Read deprecated_usage Find usages of deprecated APIs in the codebase Read detect_changes Git-diff impact analysis: detects which source files and line ranges changed (HEAD vs working tree or a custom Read explain_relationship Explain how two symbols are connected: directed paths, shared imports, and heritage (extends/implements). Retu Read file_symbols List all symbols defined in a specific file — useful to understand what a file exports or contains without rea Read find_path Find the shortest call/import path between two symbols. Useful for tracing how one module reaches another. Read flows List all detected execution flows — entry points traced through the call graph. Each flow has a name, entry po Read group_contracts Inspect extracted contracts and confidence-ranked cross-repo links from the last group sync. Supports filterin Read group_list List all configured repository groups, or show the full membership of one group. Repository groups track multi Read group_query BM25 search across all repos in a group, merged via Reciprocal Rank Fusion (RRF). Returns a unified ranked lis Read group_status Check index freshness and sync staleness for all repos in a group. Flags repos that have not been indexed or a Read group_sync Extract cross-repo contracts (exports, routes, schemas, events) from every member repo in a group and detect p Read health_report Code health signals for a scope: dead code, cycles, god nodes, orphan files, complexity hotspots Read inspect 360° view of a symbol: definition location, callers, callees, heritage (extends/implements), members, cluster, Read list_exports List all exported symbols in the repository. Helps AI understand the public API surface of the codebase. Read overview Repository summary: total nodes/edges and a full breakdown of node and edge counts by kind. Use this first to Read pr_impact Given changed files or a unified diff, compute full blast radius with risk scores (HIGH/MEDIUM/LOW), test cove Read repos List all indexed repositories with node and edge counts Read routes List all HTTP route handler mappings detected in the codebase (kind=route or route/handler/controller files) Read search BM25 keyword search across all indexed symbols — functions, classes, files, routes, etc. Optionally scope to a Read secrets Scan the knowledge graph for hardcoded secrets: API keys, passwords, tokens, private keys, high-entropy string Read similar_symbols Find symbols with similar names or structure using Levenshtein distance and kind matching. Useful for finding Read suggest_tests Suggest test cases for a symbol: call paths, suggested cases, existing tests, untested callers Read vulnerability_scan Scan the knowledge graph for OWASP vulnerabilities: SQL injection, XSS, SSRF, path traversal, command injectio

FAQ

Questions about code-intel MCP Server

Is the code-intel MCP Server MCP server safe to use without restrictions? +

The code-intel MCP Server server is primarily read-only with 28 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the code-intel MCP Server MCP server expose? +

30 tools across 1 categories: Read. 28 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on code-intel MCP Server? +

Register the code-intel MCP Server 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 code-intel MCP Server tool call.

Deterministic rules across all 30 code-intel MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CODE-INTEL →

Instant setup, no code required.

30 code-intel MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.