{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_t2zgptna99bs","handle":"iflow-mcp-edenyavin-garakr-mcp","url":"https://wellknown.network/agents/iflow-mcp-edenyavin-garakr-mcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-edenyavin-garakr-mcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-edenyavin-garakr-mcp","markdown":"https://wellknown.network/agents/iflow-mcp-edenyavin-garakr-mcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-edenyavin-garakr-mcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-edenyavin-garakr-mcp/status","claim":"https://wellknown.network/agents/iflow-mcp-edenyavin-garakr-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-edenyavin-garakr-mcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-edenyavin-garakr-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-edenyavin-garakr-mcp/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-edenyavin-garakr-mcp/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-edenyavin-garakr-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_edenyavin-garakr-mcp","summary":"Garak integration through the Model Context Protocol","description":"# MCP Server For Garak LLM Vulnerability Scanner \n\nA lightweight MCP (Model Context Protocol) server for Garak.\n\nExample:\n\nhttps://github.com/user-attachments/assets/f6095d26-2b79-4ef7-a889-fd6be27bbbda\n\n---\n\n## Tools Provided\n\n### Overview\n| Name | Description |\n|------|-------------|\n| list_model_types | List all available model types (ollama, openai, huggingface, ggml) |\n| list_models | List all available models for a given model type |\n| list_garak_probes | List all available Garak attacks/probes |\n| get_report | Get the report of the last run |\n| run_attack | Run an attack with a given model and probe |\n\n### Detailed Description\n\n- **list_model_types**\n  - List all available model types that can be used for attacks\n  - Returns a list of supported model types (ollama, openai, huggingface, ggml)\n\n- **list_models**\n  - List all available models for a given model type\n  - Input parameters:\n    - `model_type` (string, required): The type of model to list (ollama, openai, huggingface, ggml)\n  - Returns a list of available models for the specified type\n\n- **list_garak_probes**\n  - List all available Garak attacks/probes\n  - Returns a list of available probes/attacks that can be run\n\n- **get_report**\n  - Get the report of the last run\n  - Returns the path to the report file\n\n- **run_attack**\n  - Run an attack with the given model and probe\n  - Input parameters:\n    - `model_type` (string, required): The type of model to use\n    - `model_name` (string, required): The name of the model to use\n    - `probe_name` (string, required): The name of the attack/probe to use\n  - Returns a list of vulnerabilities found\n\n---\n\n## Prerequisites\n\n1. **Python 3.11 or higher**: This project requires Python 3.11 or newer.\n   ```bash\n   # Check your Python version\n   python --version\n   ```\n\n2. **Install uv**: A fast Python package installer and resolver.\n   ```bash\n   pip install uv\n   ```\n   Or use Homebrew:\n   ```bash\n   brew install uv\n   ```\n3. **Optional: Ollama**: If you want to r…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_edenyavin-garakr-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"code.security-review","name":"Security Review","confidence":0.917,"provenance":"derived"},{"slug":"ai.model-access","name":"Model Access","confidence":0.905,"provenance":"derived"}],"categories":["ai","code"],"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":"iflow-mcp_edenyavin-garakr-mcp","registry":"pypi","observedAt":"2026-11-09T08:24:38.044Z","publishedAt":"2026-02-26T10:50:55.215458Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_edenyavin-garakr-mcp","url":"https://pypi.org/project/iflow-mcp_edenyavin-garakr-mcp/","firstSeenAt":"2026-09-09T18:22:06.976Z","fetchedAt":"2026-11-09T08:23:03.928Z","normalizedAt":"2026-11-09T08:23:03.928Z"}]},"firstSeenAt":"2026-09-09T18:22:06.976Z","updatedAt":"2026-11-09T08:24:38.044Z"}