{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_y2np7g9w28pu","handle":"mindscast-mcp","url":"https://wellknown.network/agents/mindscast-mcp","links":{"self":"https://wellknown.network/agents/mindscast-mcp/record.json","html":"https://wellknown.network/agents/mindscast-mcp","markdown":"https://wellknown.network/agents/mindscast-mcp/record.md","api":"https://wellknown.network/api/v1/agents/mindscast-mcp","status":"https://wellknown.network/api/v1/agents/mindscast-mcp/status","claim":"https://wellknown.network/agents/mindscast-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mindscast-mcp/claim.json","badge":"https://wellknown.network/agents/mindscast-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mindscast-mcp/history","tools":"https://wellknown.network/api/v1/agents/mindscast-mcp/tools"},"ard":{"identifier":"urn:air::server:mindscast-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mindscast-mcp","summary":"Mindscast MCP server — extract Product Context Documents (PCDs) using YOUR LLM, send only validated JSON to api.mindscast.app. Your source code never leaves your laptop.","description":"# mindscast-mcp\n\n> Extract a Mindscast **Product Context Document (PCD)** using **your own\n> LLM** (Claude Desktop, Cursor, Claude Code, ...). Your source code never\n> leaves your laptop. We see only the structured marketing JSON you approved.\n\nThis package is the path **C** of Mindscast's PCD ingest. Paths A (landing\nURL crawl) and B (GitHub README fetch) run server-side and are simpler but\nless private. Path C is for users who want maximum control: dev/AI/OSS\nfounders, privacy-conscious teams, or anyone whose product story lives\nacross private docs we can't access.\n\nSee [`TRUST.md`](TRUST.md) for the full audit checklist + what this server\ndoes NOT do.\n\n## Quickstart (Claude Desktop)\n\n1. **Generate an API key** at https://app.mindscast.app/settings/api-keys\n\n2. **Install** in one of these ways:\n\n   ```bash\n   # Recommended: uvx (no global install)\n   # In your MCP client config (see step 3) use:  \"command\": \"uvx\", \"args\": [\"mindscast-mcp\"]\n\n   # Or pip:\n   pip install mindscast-mcp\n   ```\n\n3. **Wire to Claude Desktop**. Edit `~/Library/Application Support/Claude/claude_desktop_config.json`\n   (macOS) or the equivalent on your OS:\n\n   ```json\n   {\n     \"mcpServers\": {\n       \"mindscast\": {\n         \"command\": \"uvx\",\n         \"args\": [\"mindscast-mcp\"],\n         \"env\": {\n           \"MINDSCAST_API_KEY\": \"msk_<your generated key>\"\n         }\n       }\n     }\n   }\n   ```\n\n   Restart Claude Desktop.\n\n4. **Tell Claude** what to do, in plain English:\n\n   > Use the Mindscast extract_pcd prompt. Read my product at `/Users/me/code/wakeworth`.\n   > Emit the ProductContext JSON. Then validate_pcd it. If clean, upload_pcd\n   > with product_id \"wakeworth\".\n\n5. **Review** the JSON Claude emits **before** approving the upload tool\n   call. Your LLM client (Claude Desktop / Cursor / etc.) will ask you to\n   confirm each tool invocation.\n\nThat's it. You'll then see the PCD in\nhttps://app.mindscast.app/pcd ready for content generation.\n\n## What gets sent over the network\n\nExactly **on…","publisher":null,"homepage":"https://mindscast.app","repository":"https://github.com/yagebin79386/flowcontent/tree/main/mcp","version":"0.1.0","license":"BSL-1.1 (see https://github.com/yagebin79386/flowcontent/blob/m…","protocols":["mcp"],"tags":["claude","llm","marketing","mcp","product-context"],"pricing":null,"endpoints":[{"url":"pypi:mindscast-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"}},"derived":{"capabilities":[{"slug":"content.marketing","name":"Marketing","confidence":1,"provenance":"declared"}],"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":"mindscast-mcp","registry":"pypi","observedAt":"2026-10-22T13:23:44.819Z","publishedAt":"2026-06-26T14:08:23.488838Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mindscast-mcp","url":"https://pypi.org/project/mindscast-mcp/","firstSeenAt":"2026-09-10T06:23:09.036Z","fetchedAt":"2026-10-22T13:22:06.651Z","normalizedAt":"2026-10-22T13:22:06.651Z"}]},"firstSeenAt":"2026-09-10T06:23:09.036Z","updatedAt":"2026-10-22T13:23:44.819Z"}