{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_umbbtapevtt5","handle":"inferra-mcp","url":"https://wellknown.network/agents/inferra-mcp","links":{"self":"https://wellknown.network/agents/inferra-mcp/record.json","html":"https://wellknown.network/agents/inferra-mcp","markdown":"https://wellknown.network/agents/inferra-mcp/record.md","api":"https://wellknown.network/api/v1/agents/inferra-mcp","status":"https://wellknown.network/api/v1/agents/inferra-mcp/status","claim":"https://wellknown.network/agents/inferra-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/inferra-mcp/claim.json","badge":"https://wellknown.network/agents/inferra-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/inferra-mcp/history","tools":"https://wellknown.network/api/v1/agents/inferra-mcp/tools"},"ard":{"identifier":"urn:air::server:inferra-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"inferra-mcp","summary":"MCP server for Inferra — deterministic rule-based decisions with RAG-powered explanations","description":"# Inferra MCP Server\n\n<!-- mcp-name: io.github.zaharajabeen13-create/inferra-mcp -->\n\nUse [Inferra](https://ai-rete-rag.com) — deterministic rule-based decisions with\nRAG-powered explanations — from Claude Code, Claude Desktop, or any MCP client.\n\nThe verdict always comes from the Rete rule engine (auditable, reproducible);\nthe LLM only explains *why*, grounded in your ingested policy documents.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `decide` | Make a decision in a domain (structured facts and/or free text) |\n| `list_rules` | Inspect a domain's rules — conditions, verdicts, salience, overlaps |\n| `ingest_text` | Add policy text to a domain's knowledge base |\n| `list_documents` | Browse a domain's ingested documents |\n| `get_usage` | Check your plan and remaining monthly decision quota |\n\n## Install\n\nNo install needed with [uv](https://docs.astral.sh/uv/) — `uvx inferra-mcp`\nfetches and runs the server on demand (see the config snippets below).\n\nAlternatively, install it as a package:\n\n```bash\npip install inferra-mcp         # from PyPI\npip install ./mcp-server        # or from source, in this repo\n```\n\n## Configure\n\nFirst create an API key: sign in at [ai-rete-rag.com](https://ai-rete-rag.com),\nopen **Settings → API Keys**, and create a key (`ik_...` — shown once).\n\n### Claude Code\n\n```bash\nclaude mcp add inferra -e INFERRA_API_KEY=ik_your-key-here -- uvx inferra-mcp\n```\n\n(If you installed via pip, use `-- inferra-mcp` instead of `-- uvx inferra-mcp`.)\n\n### Claude Desktop / other clients (JSON)\n\n```json\n{\n  \"mcpServers\": {\n    \"inferra\": {\n      \"command\": \"uvx\",\n      \"args\": [\"inferra-mcp\"],\n      \"env\": {\n        \"INFERRA_API_KEY\": \"ik_your-key-here\"\n      }\n    }\n  }\n}\n```\n\n(With a pip install, set `\"command\": \"inferra-mcp\"` and drop `\"args\"`.)\n\nEnvironment variables:\n\n| Variable | Default | Purpose |\n|---|---|---|\n| `INFERRA_API_KEY` | *(none)* | Your API key — authenticates calls and ties them to your plan quota |\n| `INFERRA_API_URL` | `https://ai-ret…","publisher":{"name":"Zahara Jabeen","url":null},"homepage":"https://ai-rete-rag.com/docs-site","repository":null,"version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["decision-intelligence","mcp","model-context-protocol","rag","rete","rules-engine"],"pricing":null,"endpoints":[{"url":"pypi:inferra-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","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["data","dev"],"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":"inferra-mcp","registry":"pypi","observedAt":"2026-09-15T21:22:00.848Z","publishedAt":"2026-07-12T18:32:46.075813Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"inferra-mcp","url":"https://pypi.org/project/inferra-mcp/","firstSeenAt":"2026-09-09T22:21:38.480Z","fetchedAt":"2026-09-15T21:19:59.413Z","normalizedAt":"2026-09-15T21:19:59.413Z"}]},"firstSeenAt":"2026-09-09T22:21:38.480Z","updatedAt":"2026-09-15T21:22:00.848Z"}