io.github.MatthewTracy/yagami
Supports Google Gemini as a direct cloud model adapter/backend.
Can route through Kong as an upstream OpenAI-compatible gateway.
Works with LangChain for agent orchestration workflows.
Works with LangGraph for stateful agent workflows.
Integrates with Ollama for local model generation.
Exposes an OpenAI-compatible API (Chat Completions and Responses) and supports OpenAI as a cloud model backend.
Exports OpenTelemetry spans for distributed tracing and observability.
Exposes Prometheus metrics for operational monitoring.
Sends approval notifications to Slack channels.
Exports security and audit events to Splunk HEC.
Works with the Vercel AI SDK for building AI applications.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Yagami
An AI router that chooses models and protects privacy.
Yagami automatically routes requests to local or cloud models based on the task and your privacy policy. Detected sensitive information, including PHI, stays local under the default policy. Local models can reduce cloud API costs; more demanding work and image generation can use cloud providers when allowed.
Documentation | Gateway API | Deployment | Security | Roadmap
Watch Yagami in action

Watch the 59-second demo: local
answers, a fictional patient case kept on the machine, and cloud image
generation. The recording uses real models, synthetic patient information,
and configured providers with yagami serve. The no-credential demo below
keeps cloud routing disabled.
Related MCP server: mcp-guardian
Try it in 60 seconds
The no-credential demo uses your configured Ollama model when it is installed; otherwise it opens a clearly labeled policy-only fallback. Choose one command:
uvx yagami demo
# or: python -m pip install yagami && yagami demo
# or: docker run --rm -p 127.0.0.1:8000:8000 ghcr.io/matthewtracy/yagami:latest yagami demo --host 0.0.0.0 --allow-remoteOpen http://127.0.0.1:8000, or use
docker compose -f compose.demo.yaml up from a clone. Demo mode blocks cloud
routing while exercising the UI, policy, lineage, storage, and audit path. For
local AI answers, install Ollama and run
ollama pull llama3.2:3b-instruct-q4_K_M before starting the demo.

Yagami is for developers and platform/security teams that need to control where agent context goes and which tools it may execute. For example: a coding agent can keep repository secrets on-device and require an identity-bound, one-time approval before a dangerous tool call.
Yagami sits between software and local models, cloud LLMs, retrieval systems,
memory, and tools. Existing OpenAI SDK applications can adopt it by changing
one base_url; Yagami then classifies context locally, applies versioned
policy, and records content-free evidence for each decision.
Take the no-data security tour or run the flagship security demos for secret containment, poisoned retrieval, and identity-bound tool approval.
Protect an application
Initialize persistent user configuration, check the host, and start Yagami:
yagami init
yagami doctor
yagami serveInstall yagami[providers] when the Yagami process or the example client uses
Anthropic/OpenAI-compatible SDKs. PDF ingestion and OS key storage are separate
ingest and desktop extras; see configuration.
Then point an OpenAI client at the gateway:
from openai import OpenAI
client = OpenAI(
base_url="http://127.0.0.1:8000/v1",
api_key="your-yagami-project-key",
)
response = client.chat.completions.create(
model="yagami-auto",
messages=[{"role": "user", "content": "Summarize this document."}],
metadata={
"purpose": "internal-documentation",
"sensitivity": "none",
"session_id": "example-session",
},
)
print(response.choices[0].message.content)Supported caller sensitivity values are none, phi, phi_medical, and
secret. A caller hint can make the policy stricter; it cannot lower a
sensitivity detected by Yagami.
For production authentication, policy, and deployment settings, follow the deployment guide.
Why teams use Yagami
Deterministic containment after classification. Once context is labeled as PHI or secret, default policy permits local backends only. Sensitive history and tool results inherit the same restriction.
One governed data plane. Chat Completions, Responses, the browser chat, and MCP use the same policy, lineage, transformation, output-DLP, budget, and audit pipeline.
Policy as code. Preview and replay decisions, run regression cases in CI, and promote deterministic Ed25519-signed policy bundles.
Evidence without prompt logging. Policy passports, hash-chained audit records, Prometheus metrics, and OpenTelemetry spans carry labels, hashes, IDs, and counts rather than prompt or completion content.
Model choice without policy duplication. Route to local engines, direct cloud providers, or an existing OpenAI-compatible gateway behind one enforcement point.
Governed tools. Evaluate function tools and MCP calls before execution, require short-lived one-time approvals, and keep inbound credentials from being forwarded to downstream servers.
Core capabilities
Area | Included |
Compatible APIs | OpenAI Chat Completions, core Responses API, Streamable HTTP MCP |
Identity | Scoped project API keys and OIDC/JWT workload identity |
Policy | Versioned YAML/JSON rules, restrictive merging, preview, replay, shadow mode, regression tests, signed bundles |
Privacy | Local classification, caller sensitivity, context lineage, AES-GCM tokenization, rehydration, output DLP, optional Presidio |
Tools | Function calling, governed built-in skills, stdio and remote MCP, one-time approvals |
Operations | Spend/rate/concurrency/context limits, health checks, Prometheus, OpenTelemetry, SIEM export, approval webhooks |
Packaging | Python 3.11-3.14, PyPI, non-root container, Docker Compose, Helm, SBOMs, checksums, and build provenance |
Models and integrations
Local generation works with Ollama, llama.cpp through
the optional llama-cpp-python runtime, and Microsoft Foundry Local through
its loopback OpenAI-compatible service. Direct cloud adapters cover Anthropic,
OpenAI, Mistral, Groq, OpenRouter, Google Gemini, and Stability AI image
generation.
Yagami also works with LangChain/LangGraph, the Vercel AI SDK, Microsoft Presidio, Splunk HEC and generic SIEM webhooks, Slack and Teams approval notifications, and upstream gateways such as LiteLLM, Portkey, Kong, or Envoy. See the integration recipes.
How it compares
Yagami is not trying to replace every gateway, validator, or security scanner. Its focus is deterministic post-classification containment, governed tool execution, and content-free decision evidence. See the honest comparison guide for when LiteLLM, Guardrails AI, NeMo Guardrails, Presidio, LlamaFirewall, or a direct provider SDK is the better choice—and how to combine them with Yagami.
How enforcement works
flowchart LR
A["Application or agent"] --> B["Authentication and project limits"]
B --> C["Local classification and context lineage"]
C --> D["Versioned policy"]
D --> E{"Allowed destination or capability"}
E --> F["Local or approved model"]
E --> G["Retrieval, memory, or tool"]
F --> H["Output inspection"]
G --> H
H --> I["Response"]
D --> J["Content-free policy passport and audit chain"]
H --> JPolicy is the final authority. Slash commands and explicit backend selection cannot override a sensitive-data restriction. Classifier failures fail local by default, and cloud routes can be blocked entirely or stopped at a daily spend cap.
Important limitations
Yagami is an enforcement component, not a compliance certification. Automated detection can miss sensitive data. Strict deployments should declare sensitivity at the caller, use a local-only policy, test organization-specific cases, encrypt storage at the host or volume layer, and review the threat model.
The project is alpha. Validate policy and failure behavior against your own requirements before production use.
Documentation
Contributing
Focused issues and pull requests are welcome. Read CONTRIBUTING.md, the security policy, and the code of conduct.
License
MIT - Copyright (c) 2026 Matthew Tracy and Yagami contributors.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
MCP gateway: one connection for your AI apps, with tool policies, PII redaction and audit logs.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Related MCP Servers
AlicenseNot gradedqualityAmaintenanceOpen-source MCP proxy that enforces security policies, content scanning, and audit logging between AI agents and tool servers25AGPL 3.0- AlicenseAqualityDmaintenanceSecurity, cost, and health governance proxy for MCP infrastructure. Enforces YAML-configurable security policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features OAuth 2.1/OIDC with RBAC, web dashboard, payload normalization, semantic shell AST analysis, mTLS, and a formal STRIDE threat model.4134 npm4MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for AI agent security guardrails. Provides input validation, prompt injection detection, PII redaction, output filtering, policy enforcement, rate limiting, and comprehensive audit logging.72 npm1MIT
- FlicenseNot gradedqualityCmaintenanceA policy and audit layer for Model Context Protocol (MCP). MCP Firewall sits transparently between any MCP client (Claude Desktop, Cursor, VS Code, etc.) and an upstream MCP server, allowing you to inspect, allow, block, or audit requests before they reach the server.-