{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_z7dsn5ymepwk","handle":"iflow-mcp-vectara-vectara-mcp","url":"https://wellknown.network/agents/iflow-mcp-vectara-vectara-mcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-vectara-vectara-mcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-vectara-vectara-mcp","markdown":"https://wellknown.network/agents/iflow-mcp-vectara-vectara-mcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-vectara-vectara-mcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-vectara-vectara-mcp/status","claim":"https://wellknown.network/agents/iflow-mcp-vectara-vectara-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-vectara-vectara-mcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-vectara-vectara-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:iflow-mcp-vectara-vectara-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_vectara_vectara-mcp","summary":"A Model Context Protocol (MCP) server that provides tools from Vectara","description":"# Vectara MCP Server\n\n![GitHub Repo stars](https://img.shields.io/github/stars/Vectara/Vectara-mcp?style=social)\n![PyPI version](https://img.shields.io/pypi/v/vectara-mcp.svg)\n![License](https://img.shields.io/pypi/l/vectara-mcp.svg)\n![Security](https://img.shields.io/badge/security-first-brightgreen)\n\n> 🔌 **Compatible with [Claude Desktop](https://claude.ai/desktop), and any other MCP Client!**\n>\n> Vectara MCP is also compatible with any MCP client\n>\n\nThe Model Context Protocol (MCP) is an open standard that enables AI systems to interact seamlessly with various data sources and tools, facilitating secure, two-way connections.\n\nVectara-MCP provides any agentic application with access to fast, reliable RAG with reduced hallucination, powered by Vectara's Trusted RAG platform, through the MCP protocol.\n\n## Installation\n\nYou can install the package directly from PyPI:\n\n```bash\npip install vectara-mcp\n```\n\n## Quick Start\n\n### Secure by Default (HTTP/SSE with Authentication)\n\n```bash\n# Start server with secure HTTP transport (DEFAULT)\npython -m vectara_mcp\n# Server running at http://127.0.0.1:8000 with authentication enabled\n```\n\n### Local Development Mode (STDIO)\n\n```bash\n# For Claude Desktop or local development (less secure)\npython -m vectara_mcp --stdio\n# ⚠️ Warning: STDIO transport is less secure. Use only for local development.\n```\n\n### Configuration Options\n\n```bash\n# Custom host and port\npython -m vectara_mcp --host 0.0.0.0 --port 8080\n\n# SSE transport mode\npython -m vectara_mcp --transport sse --path /sse\n\n# Disable authentication (DANGEROUS - dev only)\npython -m vectara_mcp --no-auth\n```\n\n## Transport Modes\n\n### HTTP Transport (Default - Recommended)\n- **Security:** Built-in authentication via bearer tokens\n- **Encryption:** HTTPS ready\n- **Rate Limiting:** 100 requests/minute by default\n- **CORS Protection:** Configurable origin validation\n- **Use Case:** Production deployments, cloud environments\n\n### SSE Transport\n- **Streaming:** Server-Sent Events for r…","publisher":{"name":"Ofer Mendelevitch","url":null},"homepage":"https://github.com/vectara/vectara-mcp","repository":"https://github.com/vectara/vectara-mcp","version":"0.2.1","license":null,"protocols":["mcp"],"tags":["mcp","vectara","rag","ai","search","semantic-search"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_vectara_vectara-mcp","type":"package_pypi","auth":null,"probeable":false},{"url":"pypi:vectara-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","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"security.identity","name":"Identity & Access","confidence":0.825,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["data","dev","security"],"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":"iflow-mcp_vectara_vectara-mcp","registry":"pypi","observedAt":"2026-09-10T15:25:05.314Z","publishedAt":"2026-01-28T04:53:26.801750Z","latestVersion":"0.2.1"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_vectara_vectara-mcp","url":"https://pypi.org/project/iflow-mcp_vectara_vectara-mcp/","firstSeenAt":"2026-09-09T21:24:44.730Z","fetchedAt":"2026-09-09T21:24:44.730Z","normalizedAt":"2026-09-09T21:24:44.730Z"},{"source":"pypi","key":"vectara-mcp","url":"https://pypi.org/project/vectara-mcp/","firstSeenAt":"2026-09-10T15:23:11.606Z","fetchedAt":"2026-09-10T15:23:11.606Z","normalizedAt":"2026-09-10T15:23:11.606Z"}]},"firstSeenAt":"2026-09-09T21:24:44.730Z","updatedAt":"2026-09-10T15:25:05.314Z"}