{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_pbyqe7s4t49v","handle":"tdsql-mcp","url":"https://wellknown.network/agents/tdsql-mcp","links":{"self":"https://wellknown.network/agents/tdsql-mcp/record.json","html":"https://wellknown.network/agents/tdsql-mcp","markdown":"https://wellknown.network/agents/tdsql-mcp/record.md","api":"https://wellknown.network/api/v1/agents/tdsql-mcp","status":"https://wellknown.network/api/v1/agents/tdsql-mcp/status","claim":"https://wellknown.network/agents/tdsql-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/tdsql-mcp/claim.json","badge":"https://wellknown.network/agents/tdsql-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:tdsql-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"tdsql-mcp","summary":"MCP server for Teradata Vantage — SQL execution and native analytics function reference for AI agents","description":"# tdsql-mcp\n\nAn MCP server that turns Teradata Vantage into a full-stack analytics agent platform — giving AI agents not just SQL execution, but a structured, hierarchical knowledge base of Teradata's native function ecosystem.\n\n## What This Is\n\nMost database MCP servers provide query execution. This one goes further: it equips agents with the knowledge they need to use Teradata *correctly and optimally* — not just to run arbitrary SQL, but to reach for the right native distributed function for each step of an analytics workflow.\n\nTeradata Vantage includes hundreds of built-in table operators for ML, statistics, data preparation, text analytics, and vector search. These run distributed across all AMPs in parallel and consistently outperform equivalent hand-written SQL. The challenge for agents is *discovery* — knowing these functions exist, knowing which one to use, and knowing how to combine them into pipelines.\n\nThis server solves that with a structured syntax reference library and an agent guidance architecture that directs models toward native functions at every decision point.\n\n> **How does it work?** See [docs/architecture.md](docs/architecture.md) for a full explanation of the MCP server, Skill, and combined architectures — including diagrams of all three modes.\n\n---\n\n## Why This Matters\n\nThe conventional pattern for AI-assisted analytics looks like this:\n\n```\nAgent pulls data → processes in Python / LLM context → returns result\n```\n\nThis works at small scale but collapses under real-world conditions: the data transfer is expensive, the LLM context fills with raw data instead of insights, results are ephemeral and non-reproducible, and nothing produced is reusable at scale.\n\nThe in-database approach enabled by this server inverts that model:\n\n```\nAgent orchestrates SQL → analytics execute on the platform → only results returned\n```\n\n### Zero Data Movement\n\nNative Teradata table operators execute where the data lives — across all AMPs in parallel. No rows are…","publisher":null,"homepage":"https://github.com/ksturgeon-td/tdsql-mcp","repository":"https://github.com/ksturgeon-td/tdsql-mcp/issues","version":"1.4.3","license":"MIT","protocols":["mcp"],"tags":["ai-agent","analytics","llm","mcp","sql","teradata","vantage"],"pricing":null,"endpoints":[{"url":"pypi:tdsql-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":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.791,"provenance":"derived"}],"categories":["data","dev"],"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":"tdsql-mcp","registry":"pypi","observedAt":"2026-09-10T13:21:54.975Z","publishedAt":"2026-08-28T00:25:59.386340Z","latestVersion":"1.4.3"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"tdsql-mcp","url":"https://pypi.org/project/tdsql-mcp/","firstSeenAt":"2026-09-10T13:21:04.466Z","fetchedAt":"2026-09-10T13:21:04.466Z","normalizedAt":"2026-09-10T13:21:04.466Z"}]},"firstSeenAt":"2026-09-10T13:21:04.466Z","updatedAt":"2026-09-10T13:21:54.975Z"}