{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_a7re3vqaca6k","handle":"empirica-mcp","url":"https://wellknown.network/agents/empirica-mcp","links":{"self":"https://wellknown.network/agents/empirica-mcp/record.json","html":"https://wellknown.network/agents/empirica-mcp","markdown":"https://wellknown.network/agents/empirica-mcp/record.md","api":"https://wellknown.network/api/v1/agents/empirica-mcp","status":"https://wellknown.network/api/v1/agents/empirica-mcp/status","claim":"https://wellknown.network/agents/empirica-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/empirica-mcp/claim.json","badge":"https://wellknown.network/agents/empirica-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/empirica-mcp/history","tools":"https://wellknown.network/api/v1/agents/empirica-mcp/tools"},"ard":{"identifier":"urn:air::server:empirica-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"empirica-mcp","summary":"MCP server for Empirica — AI measurement and calibration tools via Model Context Protocol","description":"# Empirica MCP Server\n\n**AI measurement and calibration tools via Model Context Protocol.**\n\nExposes Empirica's tool surface to Claude Desktop, IDEs, and any\nMCP-compatible environment (Cursor, Gemini CLI, Codex, etc.). Track\nwhat AI knows, gate what it does, and compound learning across\nsessions — without needing Claude Code or Bash access.\n\n> **Tool surface (70 tools as of 1.11.2)** covers session lifecycle,\n> the epistemic transaction loop, artifact logging, goals, project\n> search, calibration, lessons, sync, entity registry, and (added\n> 2026-06-03) the mesh primitives: `practice_context` (Ambassador\n> addressbook), `commit_context` (temporal trail), `listener_on/arm/off`\n> (listener facade), `loop_*` (adaptive scheduler), `notify_emit`\n> (multi-backend dispatcher), `mailbox_reply` (atomic propose+complete),\n> `mesh_status` (mesh health). Run `empirica mcp-list-tools` to see\n> the live registry against your installed package.\n\n[![PyPI](https://img.shields.io/pypi/v/empirica-mcp)](https://pypi.org/project/empirica-mcp/)\n[![Python](https://img.shields.io/badge/python-3.11%2B-blue)]()\n[![License](https://img.shields.io/badge/license-MIT-green)](../LICENSE)\n\n---\n\n## Installation\n\n```bash\npip install empirica-mcp\n```\n\n**Note:** The MCP server requires the full Empirica package for stateful operations:\n\n```bash\npip install empirica  # Recommended - includes empirica-mcp\n```\n\n### Verify Installation\n\n```bash\nempirica --version      # CLI\nempirica-mcp --help     # MCP server\n```\n\n---\n\n## Quick Start\n\n### 1. Standard Mode\n\n```bash\nempirica-mcp\n```\n\nWorks as a standard MCP tool provider. No epistemic layer.\n\n### 2. Epistemic Mode\n\n```bash\nexport EMPIRICA_EPISTEMIC_MODE=true\nempirica-mcp\n```\n\nEvery tool call now includes epistemic self-awareness - the server maintains vector state and routes behavior based on confidence/uncertainty.\n\n### 3. Personality Profiles\n\n```bash\n# Cautious (investigates early)\nexport EMPIRICA_PERSONALITY=cautious_researcher\n\n# Pragmatic (action-o…","publisher":{"name":"David S. L. Van Assche","url":null},"homepage":"https://github.com/EmpiricaAI/empirica/tree/main/docs","repository":"https://github.com/EmpiricaAI/empirica/tree/main/docs","version":"1.14.20","license":null,"protocols":["mcp"],"tags":["mcp","empirica","calibration","ai","measurement","epistemic"],"pricing":null,"endpoints":[{"url":"pypi:empirica-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["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":"empirica-mcp","registry":"pypi","observedAt":"2026-11-09T04:26:38.034Z","publishedAt":"2026-11-04T14:30:05.187569Z","latestVersion":"1.14.20"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"empirica-mcp","url":"https://pypi.org/project/empirica-mcp/","firstSeenAt":"2026-09-09T14:33:06.423Z","fetchedAt":"2026-11-09T04:25:06.326Z","normalizedAt":"2026-11-09T04:25:06.326Z"}]},"firstSeenAt":"2026-09-09T14:33:06.423Z","updatedAt":"2026-11-09T04:26:38.034Z"}