Hybrid semantic and keyword code search for coding agents.
ai.takara/miru — MCP Server
The ai.takara/miru MCP server provides hybrid semantic and keyword code search for coding agents. Its purpose is to help locate relevant code using both semantic understanding and keyword matching, supporting agent-driven workflows that need targeted source retrieval.
🛠️ Key Features
Hybrid semantic and keyword code search
Designed for coding agents
🚀 Use Cases
Finding code relevant to a specific task or query
Searching with both meaning-based (semantic) and exact-term (keyword) criteria
⚡ Developer Benefits
Supports agent tooling scenarios that require code search
Improves query matching by combining semantic and keyword approaches
⚠️ Limitations
No additional capabilities, tools, or constraints are specified in the provided server data
Use Miru to find where authentication is configured in this project.
If credentials are missing, Claude can use Miru's auth tool to start sign-in. Approve the login code, then retry the search. Plugin credentials are separate from CLI credentials.
Other agents
See agent integrations for Codex and Cursor plugins. The Cursor plugin provides skills and rules; use the CLI installer below to connect its MCP tools.
Install (CLI fallback)
For terminal use or agents configured through the CLI:
bash
bun add -g @takara-ai/miru-code
miru setup
miru install
Choose your agents in the installer, then restart them. See supported integrations. Use miru uninstall to remove the configuration.
Use --json for scripts. Run miru <command> -h for options.
MCP tools
Tool
Purpose
search
Find code by meaning
locate
Find exact strings, regex matches, or filenames
expand
Read neighbouring chunks in the same file
find_related
Find similar code in other files
auth
Sign in or configure a SageMaker endpoint
read_benchmark
Read token-savings totals when benchmark mode is enabled
The optional repo argument defaults to the server's working directory. Miru builds the index on first use and watches local files for changes.
How it works
Miru combines embeddings, BM25, and code-aware ranking. Tree-sitter provides syntax-aware chunks for 26 languages, with structural and line-based fallbacks for other files.
By default, Miru sends file contents as source chunks and search queries over HTTPS to Takara for embeddings. API usage may incur costs under your Takara plan.
For embeddings on your own infrastructure, use AWS SageMaker. Set MIRU_WORKSPACE_ROOT to restrict local MCP repository paths to one directory.
Documentation
Reference: CLI commands, MCP parameters, configuration, and benchmarks
Agent integrations: plugin capabilities, configuration paths, and optional skills
Contributing: development setup, checks, and releases