Twira
@TwiraHQ
About Twira
Coding power tools for AI agents. 18 deterministic MCP tools: code-graph search, SAST, blast radius, wire-level PII redaction, signed audit chain. Works with Claude Code, Codex, Gemini, Cursor. Free tier on install.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Twira": {
"command": "twira",
"args": [
"mcp"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Twira?
Twira is a single local binary that gives AI coding agents deterministic, indexed access to a codebase. It provides 18 power tools covering code search, static analysis, dependency vulnerability scanning, a wire-level AI compliance proxy, and tamper-evident audit chains. It is built for developers and teams who want their AI agents to act on real code instead of guessing.
How to use Twira?
Install via curl, npm, or Homebrew, then run twira init inside your repo to detect your agent, write the MCP configuration, and build the first index. No signup, account, or payment is required for the free tier. Agents call Twira’s tools over MCP; you can also invoke the same tools from your terminal.
Key features of Twira
- AI Compliance Proxy: wire-level PII and secret redaction before data leaves your machine.
- Ed25519-signed, Merkle-chained receipts for every agent call.
- Code Index with call graph, symbols, and dependencies across 26 languages.
- Deterministic SAST with 65 detectors across four profiles.
- Database MCP: live schema mapping and read-only queries across six engines.
- Multi-model team coordination: ask, review, and debate across 10+ frontier models.
Use cases of Twira
- Give an AI coding agent deterministic code search and symbol lookup to reduce hallucinations.
- Redact personally identifiable information and secrets before they reach a model provider.
- Audit every agent action with cryptographically verifiable receipts for compliance regimes.
- Find bugs and dependency vulnerabilities with reachability-filtered, local-first analysis.
- Coordinate multiple agent sessions on the same repository without collisions.
FAQ from Twira
Is Twira free?
Yes, for personal use the free tier includes Index, Code Search, and Code Read with no signup or card. Pro costs $29.99/month with a 14-day trial; students with an institutional email get Pro free.
What AI agents does Twira work with?
Twira works with any agent that speaks the Model Context Protocol (MCP), including Claude Code, Codex, Gemini CLI, and Cursor.
Does my source code leave my machine?
No. All tools run locally on your machine. The AI Compliance Proxy redacts data at the wire before it reaches the model provider, and the real source code never leaves your environment.
What operating systems and runtime are required?
Twira runs on macOS, Linux, and Windows. It is a single binary with no runtime dependencies.
How does Twira handle API keys for model providers?
The AI Compliance Proxy encrypts provider API keys with AES-256-GCM and injects them at the wire. The agent never sees the key, and you can rotate keys centrally without touching every machine.
Frequently asked questions
Is Twira free?
Yes, for personal use the free tier includes Index, Code Search, and Code Read with no signup or card. Pro costs $29.99/month with a 14-day trial; students with an institutional email get Pro free.
What AI agents does Twira work with?
Twira works with any agent that speaks the Model Context Protocol (MCP), including Claude Code, Codex, Gemini CLI, and Cursor.
Does my source code leave my machine?
No. All tools run locally on your machine. The AI Compliance Proxy redacts data at the wire before it reaches the model provider, and the real source code never leaves your environment.
What operating systems and runtime are required?
Twira runs on macOS, Linux, and Windows. It is a single binary with no runtime dependencies.
How does Twira handle API keys for model providers?
The AI Compliance Proxy encrypts provider API keys with AES-256-GCM and injects them at the wire. The agent never sees the key, and you can rotate keys centrally without touching every machine.
Basic information
More AI & Agents MCP servers

Competitor Tracker & Co.
Competitor Tracker & Co.Competitor Tracker & Co. watches your competitors' websites and tells you what changed. Every week it crawls their pricing, product, messaging and corporate pages, detects the changes that matter, and files a tagged, ran
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
MCP Claude Code
SDGLBLMCP implementation of Claude Code capabilities and more
Mcp Agent
lastmile-aiBuild effective agents using Model Context Protocol and simple workflow patterns
Comments