{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_99xemwa3qnh7","handle":"kavach-mcp","url":"https://wellknown.network/agents/kavach-mcp","links":{"self":"https://wellknown.network/agents/kavach-mcp/record.json","html":"https://wellknown.network/agents/kavach-mcp","markdown":"https://wellknown.network/agents/kavach-mcp/record.md","api":"https://wellknown.network/api/v1/agents/kavach-mcp","status":"https://wellknown.network/api/v1/agents/kavach-mcp/status","claim":"https://wellknown.network/agents/kavach-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/kavach-mcp/claim.json","badge":"https://wellknown.network/agents/kavach-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/kavach-mcp/history","tools":"https://wellknown.network/api/v1/agents/kavach-mcp/tools"},"ard":{"identifier":"urn:air::server:kavach-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"kavach-mcp","summary":"Security middleware for Model Context Protocol (MCP) that detects and blocks malicious tool calls","description":"# Kavach - MCP Security Middleware\n\nSecurity middleware for Model Context Protocol (MCP) that detects and blocks malicious tool calls using pattern-based rule scanning.\n\n**Built by [Shivam Namdeo](https://www.linkedin.com/in/shivamnamdeo0101/)** | [PyPI Package](https://pypi.org/project/kavach-mcp/) | [Use Cases](https://github.com/shivamnamdeo0101/kavach-mcp-middleware-use-cases) \n\n## Quick Start\n\n```bash\n# Create and activate virtual environment\npython3 -m venv venv\nsource venv/bin/activate\n\n# Run the example\ncd example\npython3 app.py\n```\n\n## Architecture\n\n**Core Components:**\n\n- **`middleware.py`** - `KavachMiddleware`: Main entry point. Processes tool calls and returns allow/block decisions.\n- **`engine.py`** - `DetectionEngine`: Scans text against rules and collects violations.\n- **`rules.py`** - `KAVACH_RULES`: Rule definitions for detecting prompt injection, PII, API keys, etc.\n- **`types.py`** - `Rule`: Data class defining rule structure (id, name, severity, patterns).\n\n## How It Works\n\n### Sync: Content-based Blocking\n```python\nfrom kavach import KavachMiddleware\n\nmiddleware = KavachMiddleware()\n\n# Process any tool call\nresult = middleware.process({\n    \"tool\": \"aws.s3\",\n    \"access_key\": \"AKIAIOSFODNN7EXAMPLE\"\n})\n\n# Returns: {\"allowed\": False, \"violations\": [...]}\n```\n\n### Async: FastMCP Middleware Integration\n```python\nfrom fastmcp import FastMCP\nfrom kavach import KavachMiddleware\n\nmcp = FastMCP(\"my-server\")\nmcp.add_middleware(\n    KavachMiddleware(\n        sensitive_tools=[\n            \"filesystem.delete\",\n            \"aws.*\",           # wildcard patterns\n            \"database.execute\"\n        ]\n    )\n)\n```\n\n**Flow:**\n1. Tool call intercepted by `on_call_tool()` middleware hook\n2. Tool name matched against `sensitive_tools` patterns\n3. If matched, `DetectionEngine` scans arguments against rules\n4. If violations found and strict mode enabled → raises `SecurityException`\n5. Otherwise → chain to next middleware\n\n## Default Security Rules\n\n## 🛡️ Default …","publisher":{"name":"Shivam Namdeo","url":null},"homepage":"https://github.com/shivamnamdeo0101/kavach-mcp-middleware","repository":"https://github.com/shivamnamdeo0101/kavach-mcp-middleware","version":"0.1.11","license":"MIT","protocols":["mcp"],"tags":["mcp","security","middleware","detection"],"pricing":null,"endpoints":[{"url":"pypi:kavach-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.filesystem","name":"Filesystem","confidence":0.882,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"},{"slug":"infra.cloud","name":"Cloud Platforms","confidence":0.699,"provenance":"derived"}],"categories":["dev","infra"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"kavach-mcp","registry":"pypi","observedAt":"2026-11-09T12:23:39.477Z","publishedAt":"2026-06-06T12:56:36.691933Z","latestVersion":"0.1.11"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"kavach-mcp","url":"https://pypi.org/project/kavach-mcp/","firstSeenAt":"2026-09-09T22:23:06.608Z","fetchedAt":"2026-11-09T12:22:04.473Z","normalizedAt":"2026-11-09T12:22:04.473Z"}]},"firstSeenAt":"2026-09-09T22:23:06.608Z","updatedAt":"2026-11-09T12:23:39.477Z"}