Vectara MCP Server

A Model Context Protocol (MCP) server that provides tools from Vectara

Local serverstdioPython

What is the Vectara MCP server?

Connect Vectara to Claude, Cursor or any other MCP client and it stops being a tab you switch to. A Model Context Protocol (MCP) server that provides tools from Vectara. The vectara mcp server is what makes that connection.

What the server does

The 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.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • setup_vectara_api_key — **
  • api_key — str, Your Vectara API key - required
  • clear_vectara_api_key — **
  • ask_vectara — **
  • query — str, The user query to run - required
  • corpus_keys — list[str], List of Vectara corpus keys to use for the search - required
  • n_sentences_before — int, Number of sentences before the answer to include in the context - optional, default is 2
  • n_sentences_after — int, Number of sentences after the answer to include in the context - optional, default is 2
  • lexical_interpolation — float, The amount of lexical interpolation to use - optional, default is 0.005
  • max_used_search_results — int, The maximum number of search results to use - optional, default is 10
  • generation_preset_name — str, The name of the generation preset to use - optional, default is "vectara-summary-table-md-query-ext-jan-2025-gpt-4o"
  • response_language — str, The language of the response - optional, default is "eng"

Installation

vectara-mcp on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Credentials and setup notes

Configuration is passed through the environment: VECTARA_API_KEY, VECTARA_AUTHORIZED_TOKENS, VECTARA_ALLOWED_ORIGINS, VECTARA_TRANSPORT, VECTARA_AUTH_REQUIRED. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Vectara's toolset — setup_vectara_api_key, api_key, clear_vectara_api_key and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Ofer Mendelevitch; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Vectara.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
setup_vectara_api_key**
api_keystr, Your Vectara API key - required.
clear_vectara_api_key**
ask_vectara**
querystr, The user query to run - required.
corpus_keyslist[str], List of Vectara corpus keys to use for the search - required.
n_sentences_beforeint, Number of sentences before the answer to include in the context - optional, default is 2.
n_sentences_afterint, Number of sentences after the answer to include in the context - optional, default is 2.
lexical_interpolationfloat, The amount of lexical interpolation to use - optional, default is 0.005.
max_used_search_resultsint, The maximum number of search results to use - optional, default is 10.
generation_preset_namestr, The name of the generation preset to use - optional, default is "vectara-summary-table-md-query-ext-jan-2025-gpt-4o".
response_languagestr, The language of the response - optional, default is "eng".
search_vectara**
correct_hallucinations**

How to install the Vectara MCP server

{
  "mcpServers": {
    "Vectara": {
      "command": "python",
      "args": ["-m", "vectara_mcp", "--stdio"],
      "env": {
        "VECTARA_API_KEY": "your-api-key"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
VECTARA_API_KEYCredential the server authenticates with.Yes
VECTARA_AUTHORIZED_TOKENSCredential the server authenticates with.Yes
VECTARA_ALLOWED_ORIGINSConfiguration value read at startup.Optional
VECTARA_TRANSPORTConfiguration value read at startup.Optional
VECTARA_AUTH_REQUIREDConfiguration value read at startup.Optional

Example prompts to try

  • Use Vectara to setup vectara api key.
  • Use Vectara to api key.
  • Use Vectara to clear vectara api key.

Frequently asked questions

It connects Vectara to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (setup_vectara_api_key, api_key, clear_vectara_api_key, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Vectara directly.