---
title: "Answers about code search for coding agents"
description: "Direct answers to the questions developers ask about code search for coding agents: speed on large repos, context, MCP servers, tokens and index freshness."
last_updated: 2026-11-05
doc_version: "2026-11-05"
canonical: https://cocoindex.io/answers/
---

# Answers about code search for coding agents

> Direct answers to the questions developers ask about code search for coding agents: speed on large repos, context, MCP servers, tokens and index freshness.

## Questions

- [Why is my coding agent slow on a large codebase or monorepo?](https://cocoindex.io/answers/coding-agent-slow-large-codebase.md): A coding agent finds code by running text searches and reading files. In a large codebase or monorepo, each question takes more searches and more file reads before the agent can edit anything. A code index shortens that step: the agent sends one query by meaning and gets the matching code chunks with file paths and line numbers.
- [How do I give Claude Code, Cursor or Codex the whole repo as context?](https://cocoindex.io/answers/whole-repo-context.md): Give the agent a search tool over the whole repo instead of loading the repo into the prompt. A large repository can exceed the context window, and code the agent does not use still costs tokens on every turn. With cocoindex-code, run ccc index once, then connect Claude Code, Codex or Cursor through MCP.
- [What is the best MCP server for code search?](https://cocoindex.io/answers/best-mcp-server-for-code-search.md): No single MCP server is best for every code search. The choice depends on the kind of search you need (by meaning, by symbol, by structure or by keyword), where the embeddings and the index run, how the index stays fresh, the license and your client. For local semantic search without an API key, cocoindex-code is one option.
- [How do I cut the tokens my coding agent burns per turn?](https://cocoindex.io/answers/cut-coding-agent-tokens.md): A turn's input tokens are the context the agent carries: the files it read, tool output and tool definitions. Reduce what enters that context. Give the agent a code search tool that returns the matching chunks instead of whole files, keep the result count low, and disable the MCP servers you do not use.
- [How do I add semantic search over my source code for my AI assistant?](https://cocoindex.io/answers/semantic-search-source-code.md): Install cocoindex-code, index the repository, and connect it to the assistant. pipx install 'cocoindex-code[full]' installs the ccc CLI with local embedding support, so you need no API key. ccc index builds the index. ccc mcp then serves a search tool to MCP clients that launch a stdio server, and ccc search queries the same index from the terminal.
- [How do I keep a code index fresh without re-embedding everything?](https://cocoindex.io/answers/keep-code-index-fresh.md): Embed only what changed. An incremental indexer skips the files whose content is the same, re-chunks the files that changed, and reuses the stored embedding of every chunk whose text is the same. cocoindex-code works this way: ccc index re-indexes changed files, and its MCP search tool refreshes the index before each query by default.

## Sitemap

- [All answers](https://cocoindex.io/answers.md)
- [Site index (llms.txt)](https://cocoindex.io/llms.txt)
- [Markdown sitemap](https://cocoindex.io/sitemap.md)
- [XML sitemap](https://cocoindex.io/sitemap.xml)