{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2kh4fk8b76c9","handle":"sparkit-mcp","url":"https://wellknown.network/agents/sparkit-mcp","links":{"self":"https://wellknown.network/agents/sparkit-mcp/record.json","html":"https://wellknown.network/agents/sparkit-mcp","markdown":"https://wellknown.network/agents/sparkit-mcp/record.md","api":"https://wellknown.network/api/v1/agents/sparkit-mcp","status":"https://wellknown.network/api/v1/agents/sparkit-mcp/status","claim":"https://wellknown.network/agents/sparkit-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/sparkit-mcp/claim.json","badge":"https://wellknown.network/agents/sparkit-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/sparkit-mcp/history","tools":"https://wellknown.network/api/v1/agents/sparkit-mcp/tools"},"ard":{"identifier":"urn:air::server:sparkit-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"sparkit-mcp","summary":"MCP server for SPARKIT — call the scientific research agent from Claude Desktop, Cursor, and other MCP clients.","description":"# sparkit-mcp\n\nMCP server for [SPARKIT](https://sparkit.science) — call the scientific\nresearch agent from Claude Desktop, Cursor, Claude Code, or any other\nMCP-compatible client.\n\nTwo tools are exposed:\n\n- **`research`** — submit a scientific question. SPARKIT searches the\n  literature, reads the relevant papers, and returns a cited Markdown\n  report. Blocks until the job finishes (default 4 min) and returns the\n  full report inline.\n- **`get_job_status`** — fetch a previously-submitted job by id. Useful\n  when `research` returned before the job finished, or to revisit a\n  past report.\n\n## Install\n\n```bash\nuv tool install sparkit-mcp\n```\n\nOr with pip:\n\n```bash\npip install sparkit-mcp\n```\n\nEither installs a `sparkit-mcp` console script. (Pre-release: install\nstraight from GitHub with\n``uv tool install \"git+https://github.com/SPARKIT-science/sparkit-mcp.git\"``\nuntil the first PyPI release lands.)\n\n## Get an API key\n\n1. Sign up at https://app.sparkit.science/signup (Try-it costs $10 for\n   5 queries; subscriptions start at $50/mo).\n2. Visit https://app.sparkit.science/keys and create a key.\n3. Copy the key — it's shown only once.\n\n## Configure your MCP client\n\n### Claude Desktop\n\nEdit `claude_desktop_config.json`:\n\n- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\n- Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n\nAdd:\n\n```json\n{\n  \"mcpServers\": {\n    \"sparkit\": {\n      \"command\": \"sparkit-mcp\",\n      \"env\": {\n        \"SPARKIT_API_KEY\": \"sk_sparkit_...\"\n      }\n    }\n  }\n}\n```\n\nRestart Claude Desktop. You should see `sparkit` appear in the tools\nicon next to the chat input.\n\nIf `sparkit-mcp` isn't on Claude Desktop's PATH (common with `uv tool`),\nuse the absolute path:\n\n```json\n\"command\": \"/Users/you/.local/bin/sparkit-mcp\"\n```\n\n(Find the path with `which sparkit-mcp` after `uv tool install`.)\n\n### Cursor\n\nEdit `~/.cursor/mcp.json` (or `.cursor/mcp.json` in your project):\n\n```json\n{\n  \"mcpServers\": {\n    \"sparkit\": {\n      \"command\": \"…","publisher":null,"homepage":"https://sparkit.science","repository":"https://github.com/SPARKIT-science/sparkit-mcp/issues","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["mcp","sparkit","research","science","agent","anthropic"],"pricing":null,"endpoints":[{"url":"pypi:sparkit-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":"research.academic","name":"Academic Research","confidence":0.825,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev","research"],"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":"sparkit-mcp","registry":"pypi","observedAt":"2026-11-04T01:24:48.839Z","publishedAt":"2026-05-05T16:14:48.285290Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"sparkit-mcp","url":"https://pypi.org/project/sparkit-mcp/","firstSeenAt":"2026-09-10T12:23:07.300Z","fetchedAt":"2026-11-04T01:23:06.946Z","normalizedAt":"2026-11-04T01:23:06.946Z"}]},"firstSeenAt":"2026-09-10T12:23:07.300Z","updatedAt":"2026-11-04T01:24:48.839Z"}