Skip to main content
Glama

Embeddings, Rerank & Speech-to-Text (Tanod)

embed_multimodal

Read-onlyIdempotent

mlpeek: Create multimodal embeddings: images and text in one vector space. For text only use embed_texts. Returns 768-dim vectors of texts and images (URL or base64) in ONE space (EmbeddingGemma 2), comparable by dot product; dimensions 512/256/128, input_type text prefix, image_detail low/standard/high. At most 16 low, 8 standard or 4 high-detail images (10 MB each, public URLs). Over 4,096 text tokens or a bad image (named by index) is a 422; an unavailable model a 503 (none charged). Typically 0.05 s per short text and 1.5-3 s per image (6.5 s at high detail), plus a few seconds on first use. Price: USD 0.002 per item (1-16 items per call: USD 0.002-0.032). Free: 5 mlpeek calls per IP per UTC day. The submitted text is never logged or stored. Docs: https://tanod.dev/learn/embeddings-rerank-ner-mcp-server.html

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": {
      "items": "<items>"
    },
    "name": "embed_multimodal"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYes1-16 items, each {text}, {image_url} or {image_base64}; every vector lands in one shared space. Priced per item.
encodingNobase64 = little-endian float32 bytes.float
dimensionsNo768 (default), 512, 256 or 128: the leading values, re-normalised (Matryoshka).
input_typeNoTask prefix for text items (images get none): query (search query), document (search corpus), question, fact_check, code_query, classification, clustering, similarity or none.none
image_detailNoVision tokens per image: low (70), standard (140) or high (280, slowest). At most 16 low, 8 standard or 4 high images per call.standard

Output Schema

NameRequiredDescriptionDefault
dataNo
noteNo
errorNoOnly on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
modelNo
usageNo
encodingNo
dimensionsNo
input_typeNo
normalizedNo
image_detailNo
prefix_appliedNo
max_tokens_per_textNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changed
    • removedInput schema / $defs / MMItem / properties / image_base64 / default
      Removed value: -null
    • removedInput schema / $defs / MMItem / properties / image_base64 / title
      Removed value: -"Image Base64"
    • removedInput schema / $defs / MMItem / properties / image_url / default
      Removed value: -null
    • removedInput schema / $defs / MMItem / properties / image_url / title
      Removed value: -"Image Url"
    • removedInput schema / $defs / MMItem / properties / text / default
      Removed value: -null
    • removedInput schema / $defs / MMItem / properties / text / title
      Removed value: -"Text"
    • removedInput schema / $defs / MMItem / title
      Removed value: -"MMItem"
    • removedInput schema / properties / dimensions / title
      Removed value: -"Dimensions"
    • removedInput schema / properties / encoding / title
      Removed value: -"Encoding"
    • removedInput schema / properties / image_detail / title
      Removed value: -"Image Detail"
    • removedInput schema / properties / input_type / title
      Removed value: -"Input Type"
    • removedInput schema / properties / items / title
      Removed value: -"Items"
    • removedInput schema / title
      Removed value: -"embed_multimodalArguments"
    • removedOutput schema / properties / data / items
      Removed value: -{
      -  "properties": {
      -    "embedding": {
      -      "type": [
      -        "array",
      -        "string",
      -        "null"
      -      ]
      -    },
      -    "image": {
      -      "type": [
      -        "object",
      -        "null"
      -      ]
      -    },
      -    "image_tokens": {
      -      "type": [
      -        "integer",
      -        "null"
      -      ]
      -    },
      -    "index": {
      -      "type": [
      -        "integer",
      -        "null"
      -      ]
      -    },
      -    "notes": {
      -      "items": {
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "type": [
      -        "array",
      -        "null"
      -      ]
      -    },
      -    "tokens": {
      -      "type": [
      -        "integer",
      -        "null"
      -      ]
      -    },
      -    "truncated": {
      -      "type": [
      -        "boolean",
      -        "null"
      -      ]
      -    },
      -    "type": {
      -      "enum": [
      -        "text",
      -        "image",
      -        null
      -      ],
      -      "type": [
      -        "string",
      -        "null"
      -      ]
      -    }
      -  },
      -  "type": [
      -    "object",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / model / properties
      Removed value: -{
      -  "alias": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "base_model": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "id": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "license": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "revision": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  },
      -  "source": {
      -    "type": [
      -      "string",
      -      "null"
      -    ]
      -  }
      -}
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes far beyond the annotations: per-IP free tier (5 calls/UTC day), per-item pricing with the resulting call range, latency estimates including cold start, and exact failure semantics (422 for oversized text or a bad image named by index, 503 for unavailable model with no charge). It also discloses that submitted text is never logged or stored, which is the kind of trust-relevant detail annotations cannot convey.

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?

Front-loaded with purpose and the sibling routing rule, then returns, parameters, limits, errors, performance, price, and privacy in a logical order. It is a single dense block and the parameter recap near the top partially duplicates the schema, but nearly every sentence carries operational weight.

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

Completeness5/5

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

An output schema exists, so return shape need not be explained, yet the description still gives the useful fact that all vectors share one space and are comparable by dot product. Combined with limits, error codes, cost, and latency, an agent has everything needed to call this correctly and budget for it.

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 description coverage is 100%, so the schema already documents every parameter including the Matryoshka `dimensions`, the `input_type` prefixes, and the per-detail image caps. The description largely restates those facts (768-dim, 512/256/128, image_detail low/standard/high) rather than adding new semantics, so the baseline 3 applies.

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 ('Create multimodal embeddings: images and text in one vector space') and immediately names the sibling it is not ('For text only use embed_texts'). An agent can distinguish this from embed_texts without opening either schema.

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

Usage Guidelines4/5

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

Explicit routing rule: text-only work goes to embed_texts, so this tool is for mixed image+text or image-only batches. It also supplies concrete selection constraints (max 16 low / 8 standard / 4 high images, 10 MB, public URLs). It stops short of advising when to pick a given `dimensions` or `input_type` combination for retrieval vs clustering, which is left to the schema enums.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.