Skip to main content
Glama
Venice MCP Server

Venice MCP Server

Official
by veniceai

Venice Embeddings

venice_embeddings

Compute OpenAI-compatible text embeddings for up to 128 inputs per call, batching larger jobs to avoid oversized requests and using wallet or API key auth.

Instructions

Compute embeddings for text input (OpenAI-compatible). Accepts up to 128 texts per call; split larger jobs into separate batches. Oversized batches are rejected before submission. Supports x402 wallet auth (no Venice account needed) and API key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "input": "<input>",
      "model": "<model>"
    },
    "name": "venice_embeddings"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesText or array of at most 128 texts.
modelYesEmbedding model id.
encoding_formatNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.1
    • changedInput schema / properties / input / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "items": {
      -      "type": "string"
      -    },
      -    "type": "array"
      -  }
      -]New value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "type": "string"
      +    },
      +    "maxItems": 128,
      +    "type": "array"
      +  }
      +]
    • changedInput schema / properties / input / description
      Previous value: -"Text or array of texts."New value: +"Text or array of at most 128 texts."
  2. Changed2 schema fields changedv0.3.0
    • addedInput schema / properties / model / minLength
      Added value: +1
    • changedInput schema / required
      Previous value: -[
      -  "input"
      -]New value: +[
      +  "input",
      +  "model"
      +]
  3. First observedv0.2.0

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a non-read-only, non-idempotent profile but say nothing useful about auth or limits, so the description carries real weight here: it discloses two supported auth paths (x402 wallet, no Venice account required, or API key) and that oversized batches are rejected before submission. It does not explain the return payload or how encoding_format changes output, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the operation before the batching rule and auth detail; nothing is wasted. Minor redundancy where the 128 limit restates the schema rather than adding to it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter tool with no output schema, the definition covers input limits and auth but leaves the response side entirely unspecified — no mention of vector dimensionality, ordering, or what base64 encoding returns. The 'OpenAI-compatible' note partially compensates, but an agent still has to infer return structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, so the baseline is 3. The description's 128-item ceiling duplicates what the schema already encodes in maxItems and the input description, and it never addresses the undocumented encoding_format enum or what 'model' identifiers are valid, so it adds little beyond structured data.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Compute embeddings for text input') and adds a disambiguating qualifier ('OpenAI-compatible') that tells an agent exactly what shape of operation and payload to expect. No sibling in the list does embeddings, so no differentiation is needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an operational usage rule — max 128 texts per call, split larger jobs into separate batches — but never states when to choose this tool over alternatives (e.g. retrieval-style embeddings vs. chat) or what prerequisites/model selection look like. Usage is implied by the batching constraint rather than explicitly framed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.