Tanod MCP server

mlpeek: embed text and images in one vector space

embed_multimodal

Read-onlyIdempotent

Generate embeddings for text and images into one shared 768-dim vector space for cross-modal similarity, search, and dot-product comparison.

Instructions

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

Input Schema

TableJSON Schema

Name	Required	Description	Default
`items`	Yes	1-16 items, each {text}, {image_url} or {image_base64}; every vector lands in one shared space. Priced per item.
`encoding`	No	base64 = little-endian float32 bytes.	float
`dimensions`	No	768 (default), 512, 256 or 128: the leading values, re-normalised (Matryoshka).
`input_type`	No	Task 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_detail`	No	Vision 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

TableJSON Schema

Name	Required	Description
`data`	No
`note`	No
`error`	No	Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
`model`	No
`usage`	No
`encoding`	No
`dimensions`	No
`input_type`	No
`normalized`	No
`image_detail`	No
`prefix_applied`	No
`max_tokens_per_text`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Oct 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: per-image count caps by detail level, 10 MB and public-URL restrictions, 4,096-token cutoff, 422/503 failure semantics ('none charged'), latency ranges, per-item pricing, free-tier rate limit, and the privacy guarantee that text is never logged.

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 text-only alternative before any constraints. It is a dense block of parentheticals (limits, errors, latency, pricing) but nearly every clause carries operational information an agent needs; only mild redundancy with the schema keeps it from a 5.

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-format details are unnecessary, and the description still covers limits, error codes, cost, rate limiting and privacy. For a paid multimodal tool with hard per-call caps, nothing an agent needs to call it correctly is missing.

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 every parameter including enum values, defaults and per-detail image caps is already documented in the schema. The description restates dimensions, input_type and image_detail almost verbatim, adding little beyond what the structured fields provide; 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 it 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 Guidelines5/5

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

Explicit routing rule: use embed_texts for text-only work, this tool when images are involved in the same shared space. The condition that selects the alternative is stated outright rather than left to inference.

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

Deploy Server