{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_khemsuqbk9em","handle":"ohwise-mcp","url":"https://wellknown.network/agents/ohwise-mcp","links":{"self":"https://wellknown.network/agents/ohwise-mcp/record.json","html":"https://wellknown.network/agents/ohwise-mcp","markdown":"https://wellknown.network/agents/ohwise-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ohwise-mcp","status":"https://wellknown.network/api/v1/agents/ohwise-mcp/status","claim":"https://wellknown.network/agents/ohwise-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ohwise-mcp/claim.json","badge":"https://wellknown.network/agents/ohwise-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:ohwise-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ohwise-mcp","summary":"MCP server exposing graph-native code context, document retrieval, schema ranking, document store, cache, and agent pipeline tools.","description":"# ohwise-mcp\n\n[![PyPI version](https://img.shields.io/pypi/v/ohwise-mcp.svg)](https://pypi.org/project/ohwise-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/ohwise-mcp.svg)](https://pypi.org/project/ohwise-mcp/)\n[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE)\n\n**MCP server connecting AI coding agents to graph-native code context and multi-agent pipelines.**\n\n`ohwise-mcp` implements the [Model Context Protocol](https://modelcontextprotocol.io/) so that any MCP-compatible AI agent (Claude Code, Claude Desktop, and others) can:\n\n- Build and query **knowledge graphs** from code repositories via [codebase2graph](https://github.com/jw-open/codebase2graph)\n- Build and query **knowledge graphs** from documents via [docs2graph](https://github.com/jw-open/docs2graph)\n- Rank the most relevant nodes for any query using **Personalized PageRank**\n- Trigger and poll **OhWise Studio pipelines** for multi-agent task execution\n\n**Pure Python. No LLM dependency for graph tools. Bring your own model.**\n\n---\n\n## Quick start\n\n```bash\npip install ohwise-mcp[all]\n```\n\n### Add to Claude Code\n\n```bash\nclaude mcp add ohwise -- ohwise-mcp\n```\n\nOr manually in your Claude Code config (`~/.claude.json` or `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"ohwise\": {\n      \"command\": \"ohwise-mcp\",\n      \"env\": {\n        \"OHWISE_URL\": \"https://your-ohwise-instance.com\",\n        \"OHWISE_TOKEN\": \"your-token-here\"\n      }\n    }\n  }\n}\n```\n\n> `OHWISE_URL` and `OHWISE_TOKEN` are only required for Studio pipeline tools. Graph tools work offline without them.\n\n---\n\n## Tools\n\n### Code graph tools\n\n| Tool | Description |\n|------|-------------|\n| `build_code_graph(repo_path, graph_type)` | Extract a knowledge graph from a code repository |\n| `rank_code_nodes(query, graph_id, k)` | Rank nodes by relevance to a query — get focused code context |\n| `search_code_graph(keyword, graph_id, kind_filter)` | Find nodes by keyword or kind (function, class, file, …) |\n\n**Graph types**:…","publisher":null,"homepage":"https://github.com/jw-open/ohwise-mcp","repository":"https://github.com/jw-open/ohwise-mcp/blob/main/CHANGELOG.md","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["agents","claude-code","code-analysis","context-engineering","knowledge-graph","llm","mcp","model-context-protocol","multi-agent","pagerank","rag"],"pricing":null,"endpoints":[{"url":"pypi:ohwise-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":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"automation.orchestration","name":"Agent Orchestration","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.825,"provenance":"derived"}],"categories":["automation","data","dev","knowledge"],"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":"ohwise-mcp","registry":"pypi","observedAt":"2026-09-10T08:27:36.882Z","publishedAt":"2026-06-08T13:35:19.482042Z","latestVersion":"0.2.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ohwise-mcp","url":"https://pypi.org/project/ohwise-mcp/","firstSeenAt":"2026-09-10T08:26:15.231Z","fetchedAt":"2026-09-10T08:26:15.231Z","normalizedAt":"2026-09-10T08:26:15.231Z"}]},"firstSeenAt":"2026-09-10T08:26:15.231Z","updatedAt":"2026-09-10T08:27:36.882Z"}