code-index-mcp

A Model Context Protocol (MCP) server (Python) that indexes and analyzes local code repositories to help LLMs search for code patterns/files and generate structured summaries (shallow file index and optional deep symbol index via tree-sitter).

Evaluated Mar 30, 2026 (22d ago)

Repo ↗ DevTools mcp code-search code-indexing tree-sitter repository-analysis developer-tools

⚙ Agent Friendliness

/ 100

Can an agent use this?

🔒 Security

/ 100

Is it safe for agents?

⚡ Reliability

/ 100

Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality

Documentation

Error Messages

Auth Simplicity

100

Rate Limits

🔒 Security

TLS Enforcement

Auth Strength

Scope Granularity

Dep. Hygiene

Secret Handling

Operates locally (no auth described), reducing credential exposure but increasing risk if misconfigured project paths or local permissions are used. README does not discuss data exfiltration, sandboxing, or logging/redaction of sensitive code contents. Dependencies include watchdog, tree-sitter, and mcp; specific CVE/status is not provided in the provided content.

⚡ Reliability

Uptime/SLA

Version Stability

Breaking Changes

Error Recovery

Best When

You have a local codebase and an MCP-capable AI client that can launch/connect to stdio-based MCP servers to perform search and symbol-aware analysis.

Avoid When

You need fine-grained access control, multi-tenant isolation, or a cloud-hosted service with built-in auth/session management.

Use Cases

• Code review assistance (find usages of APIs or patterns)
• Refactoring guidance (where functions/classes are referenced)
• Documentation generation from code structure
• Debugging support (locate error handling and related code paths)
• Architecture and component discovery in multi-language projects

Not For

• Handling remote/hosted repositories without local checkout (server is described as indexing a project path on the local filesystem)
• A secure multi-tenant SaaS API where authentication/authorization between users is required
• Use as a general-purpose code search engine without an MCP-capable client

Interface

REST API

GraphQL

gRPC

MCP Server

Yes

SDK

Webhooks

Authentication

OAuth: No Scopes: No

No authentication mechanisms are described; the MCP server is launched locally via stdio (uvx/command args) and operates on a provided project path.

Pricing

Free tier: No

Requires CC: No

Repository/package is MIT licensed; pricing for a hosted service is not described (appears to be a local tool).

Agent Metadata

Pagination

page-based

Idempotent

False

Retry Guidance

Not documented

Known Gotchas

⚠ Deep symbol extraction may require running build_deep_index before get_file_summary to avoid needs_deep_index responses.
⚠ Regex search notes indicate the basic fallback is literal-only; regex=True may require an external native search tool to be installed/detected.
⚠ Auto-refresh relies on watchdog and OS file watching; in some environments it may fail without watchdog/polling configuration.

Alternatives

MCP-compatible code search/indexers (e.g., Sourcegraph-based workflows, ripgrep/ctags/tree-sitter pipelines) Local tooling combinations: ripgrep/ugrep for search + language servers (LSP) for symbol extraction IDE/indexer approaches (e.g., ctags/universal-ctags + AST tooling)

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for code-index-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-03-30.