{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_3nhg9bkggds9","handle":"pytigergraph-mcp","url":"https://wellknown.network/agents/pytigergraph-mcp","links":{"self":"https://wellknown.network/agents/pytigergraph-mcp/record.json","html":"https://wellknown.network/agents/pytigergraph-mcp","markdown":"https://wellknown.network/agents/pytigergraph-mcp/record.md","api":"https://wellknown.network/api/v1/agents/pytigergraph-mcp","status":"https://wellknown.network/api/v1/agents/pytigergraph-mcp/status","claim":"https://wellknown.network/agents/pytigergraph-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/pytigergraph-mcp/claim.json","badge":"https://wellknown.network/agents/pytigergraph-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:pytigergraph-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"pyTigerGraph-mcp","summary":"Model Context Protocol (MCP) server for TigerGraph","description":"# pyTigerGraph-mcp\n\nModel Context Protocol (MCP) server for TigerGraph — lets AI agents interact with TigerGraph through the MCP standard. All tools use pyTigerGraph's async APIs for optimal performance.\n\n## Table of Contents\n\n- [Requirements](#requirements)\n- [Installation](#installation)\n- [Getting Started](#getting-started)\n- [Usage](#usage)\n  - [Running the MCP Server](#running-the-mcp-server)\n  - [Configuration](#configuration)\n  - [Multiple Connection Profiles](#multiple-connection-profiles)\n  - [Using with Existing Connection](#using-with-existing-connection)\n- [Client Examples](#client-examples)\n  - [Using MultiServerMCPClient](#using-multiserverMCPclient)\n  - [Using MCP Client SDK Directly](#using-mcp-client-sdk-directly)\n- [Available Tools](#available-tools)\n- [LLM-Friendly Features](#llm-friendly-features)\n  - [Structured Responses](#structured-responses)\n  - [Rich Tool Descriptions](#rich-tool-descriptions)\n  - [Token Optimization](#token-optimization)\n  - [Tool Discovery](#tool-discovery)\n- [Notes](#notes)\n\n## Requirements\n\n- **Python 3.10, 3.11, or 3.12**\n- **TigerGraph 4.1 or later** — Install from the [TigerGraph Downloads page](https://dl.tigergraph.com/) or use [TigerGraph Savanna](https://savanna.tgcloud.io/) for a managed cloud instance.\n\n> **Recommended: TigerGraph 4.2+** to enable TigerVector and advanced hybrid retrieval features.\n\n## Installation\n\n```bash\npip install pyTigerGraph-mcp\n```\n\nThis installs:\n- `pyTigerGraph>=2.0.1` — the TigerGraph Python SDK\n- `mcp>=1.0.0` — the MCP SDK\n- `pydantic>=2.0.0` — for data validation\n- `click` — for the CLI entry point\n- `python-dotenv>=1.0.0` — for loading `.env` files\n\nTo enable the `tigergraph__generate_gsql` and `tigergraph__generate_cypher` tools (LLM-powered query generation):\n\n```bash\npip install \"pyTigerGraph-mcp[llm]\"\n```\n\n> **Migrating from `pyTigerGraph[mcp]`?** `pip install pyTigerGraph[mcp]` now installs `pyTigerGraph-mcp` automatically. Update your imports from `pyTigerGraph.mcp` to `tig…","publisher":null,"homepage":"https://docs.tigergraph.com/pytigergraph/current/intro/","repository":"https://github.com/tigergraph/tigergraph-mcp/issues","version":"1.0.1","license":"Apache-2.0","protocols":["mcp"],"tags":["tigergraph","mcp","model","context","protocol","ai","graph","database"],"pricing":null,"endpoints":[{"url":"pypi:pytigergraph-mcp","type":"package_pypi","auth":null,"probeable":false},{"url":"pypi:tigergraph-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":"data.database","name":"Databases","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"}],"categories":["data","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":"pytigergraph-mcp","registry":"pypi","observedAt":"2026-09-10T14:24:22.427Z","publishedAt":"2026-04-09T04:07:38.454683Z","latestVersion":"1.0.1"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"pytigergraph-mcp","url":"https://pypi.org/project/pytigergraph-mcp/","firstSeenAt":"2026-09-10T10:24:52.231Z","fetchedAt":"2026-09-10T10:24:52.231Z","normalizedAt":"2026-09-10T10:24:52.231Z"},{"source":"pypi","key":"tigergraph-mcp","url":"https://pypi.org/project/tigergraph-mcp/","firstSeenAt":"2026-09-10T14:22:27.202Z","fetchedAt":"2026-09-10T14:22:27.202Z","normalizedAt":"2026-09-10T14:22:27.202Z"}]},"firstSeenAt":"2026-09-10T10:24:52.231Z","updatedAt":"2026-09-10T14:24:22.427Z"}