{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2pkguprmgtds","handle":"simba-mcp","url":"https://wellknown.network/agents/simba-mcp","links":{"self":"https://wellknown.network/agents/simba-mcp/record.json","html":"https://wellknown.network/agents/simba-mcp","markdown":"https://wellknown.network/agents/simba-mcp/record.md","api":"https://wellknown.network/api/v1/agents/simba-mcp","status":"https://wellknown.network/api/v1/agents/simba-mcp/status","claim":"https://wellknown.network/agents/simba-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/simba-mcp/claim.json","badge":"https://wellknown.network/agents/simba-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/simba-mcp/history","tools":"https://wellknown.network/api/v1/agents/simba-mcp/tools"},"ard":{"identifier":"urn:air::server:simba-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"simba-mcp","summary":"MCP server for Simba Marketing Mix Modeling — connect AI assistants to your MMM models","description":"# Simba MCP Server\n\n[![PyPI](https://img.shields.io/pypi/v/simba-mcp)](https://pypi.org/project/simba-mcp/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)\n\n[Simba](https://simba-mmm.com) is a Bayesian Marketing Mix Modeling (MMM) platform. This Marketing Mix Modeling [MCP server](https://modelcontextprotocol.io/) lets AI assistants interact with your models directly — upload data, build models, check results, and run budget optimizations through natural language in Claude, Cursor, or Claude Code.\n\n## Installation\n\nFor job-specific startup catalogues, see [tool profiles](docs/tool-profiles.md).\nFor instructions that help your AI assistant choose tools and interpret results, see\n[AI workflow instructions](docs/workflow-guidance.md). Read them through MCP or\ninstall them as Skills in a compatible client. Connecting MCP does not install\nSkills. [Candidate acceptance](docs/role-candidate-acceptance.md)\nrecords tested configurations and remaining rollout checks.\n\n```bash\npip install simba-mcp\n```\n\nOr run directly without installing:\n\n```bash\nuvx simba-mcp\n```\n\n## Quick Start\n\n### Cursor IDE\n\nAdd to your Cursor MCP settings (`.cursor/mcp.json` in the workspace or global settings):\n\n```json\n{\n  \"mcpServers\": {\n    \"simba\": {\n      \"command\": \"uvx\",\n      \"args\": [\"simba-mcp\"],\n      \"env\": {\n        \"SIMBA_API_URL\": \"https://demo.simba-mmm.com\",\n        \"SIMBA_API_KEY\": \"simba_sk_...\"\n      }\n    }\n  }\n}\n```\n\n### Claude Code\n\nAdd to your Claude Code MCP config:\n\n```json\n{\n  \"mcpServers\": {\n    \"simba\": {\n      \"command\": \"uvx\",\n      \"args\": [\"simba-mcp\"],\n      \"env\": {\n        \"SIMBA_API_URL\": \"https://demo.simba-mmm.com\",\n        \"SIMBA_API_KEY\": \"simba_sk_...\"\n      }\n    }\n  }\n}\n```\n\n### Claude API (MCP Connector)\n\nUse the remote Streamable HTTP transport with the Anthropic MCP connector:\n\n```python\nimport anthropic\n\nclient = anthro…","publisher":null,"homepage":"https://docs.simba-mmm.com","repository":"https://github.com/getsimba-ai/simba-mcp","version":"0.18.0","license":null,"protocols":["mcp"],"tags":["bayesian","marketing-mix-model","mcp","mmm","simba"],"pricing":null,"endpoints":[{"url":"pypi:simba-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"}},"derived":{"capabilities":[{"slug":"content.marketing","name":"Marketing","confidence":1,"provenance":"derived"}],"categories":["content"],"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":"simba-mcp","registry":"pypi","observedAt":"2026-10-22T20:24:25.402Z","publishedAt":"2026-10-14T06:37:37.949955Z","latestVersion":"0.18.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"simba-mcp","url":"https://pypi.org/project/simba-mcp/","firstSeenAt":"2026-09-10T12:22:09.276Z","fetchedAt":"2026-10-22T20:22:43.823Z","normalizedAt":"2026-10-22T20:22:43.823Z"}]},"firstSeenAt":"2026-09-10T12:22:09.276Z","updatedAt":"2026-10-22T20:24:25.402Z"}