Skip to content
Vector Panda logo

Vector Panda MCP server

Which MCP servers are Vector Panda's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to Vector Panda

Whose server it is
  • Registry namecom.vectorpanda/docsverified in the MCP registry

The registry name sits under vectorpanda.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools8
  • Server calls itselfvector-panda-docs
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 9 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer39 ms
  • Space in an agent's context≈ 675 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · search product catalogues, documents or images by meaning
  • cannot · store embeddings produced by their own model
  • not sure · run a semantic movie search from plot descriptions

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers8 tools · read 2026-10-25
  • search_docs

    Full-text search across Vector Panda concepts, tutorials, projects, and the engineering build log. Returns ranked matches with canonical URLs and freshness.

  • read_doc

    Fetch the full Markdown of one document by its site path (for example /docs/concepts/embeddings-101), as returned by search_docs.

  • get_quickstart

    The Vector Panda quickstart: install the veep Python SDK, upload a file, and run similarity queries end to end.

  • get_api_operation

    List public REST API operations, or pass one (e.g. "POST /api/v1/query") for its parameters, request body, responses, and auth. Sourced from the published OpenAPI spec.

  • get_pricing

    Current storage-tier pricing, monthly usage credits, and billing cycle. Storage-only pricing: no per-query or egress fees.

  • get_benchmark_methodology

    Measured benchmark results and full reproduction methodology (VectorDBBench through the public API), including dataset, recall, and cost.

  • compare_storage_tiers

    Hot, warm, and paused storage tiers: current per-GB prices with what each tier means for query latency and when to pick it.

  • list_supported_formats

    File formats accepted for vector ingestion, from the canonical features page.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "docs": {
      "type": "http",
      "url": "https://www.vectorpanda.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http vectorpanda https://www.vectorpanda.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://www.vectorpanda.com/mcp as a custom connector in the settings.

Other servers listed as Vector Panda's
  • com.vectorpanda/databaseanswers, requires sign-inverified in the MCP registry

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.