eggnog-mcp

get_orthologs

Retrieve pairwise orthologs for an eggNOG protein ID, returning orthologous proteins grouped by species with an optional max species limit.

Instructions

Retrieve pairwise orthologs for a protein.

Returns the orthologous proteins grouped by species for the given eggNOG protein ID.

Parameters

protein_id : str The eggNOG protein identifier in taxid.seqid format. Example: 9606.ENSP00000269305 max_species : int, optional Maximum number of species to include (default 50).

Returns

str JSON string with orthologs grouped by species.

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": {
      "protein_id": "<protein_id>"
    },
    "name": "get_orthologs"
  }
}

Input Schema

Name	Required	Description	Default
`protein_id`	Yes
`max_species`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 19, 2026

TDQS

B3.1/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It does not state whether this is read-only, whether authentication or rate limits apply, or — importantly for max_species — whether results are truncated and how ties are broken. Only the 'grouped by species' return shape is disclosed.

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?

The numpydoc-style layout is front-loaded and scannable, with purpose first and parameters clearly enumerated. The Returns block is somewhat redundant given the output schema exists, but the whole is short and earns most of its space.

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 simple two-parameter retrieval tool with an output schema, the essential call information (id format, species cap) is present. What is missing is routing guidance versus sibling tools and any statement about truncation behavior or safety profile, leaving modest gaps.

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

Parameters4/5

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

Schema description coverage is 0%, yet the description compensates well: it documents the required protein_id format (``taxid.seqid``) with a concrete example and the optional max_species default. This adds real meaning the bare schema lacks, though it does not explain the consequence of raising or lowering max_species.

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

Purpose4/5

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

States a specific verb and resource ('Retrieve pairwise orthologs for a protein') with the required identifier. It is distinguishable from get_protein and search_eggnog, but it never explicitly names how it differs from the closely related get_orthologous_group, so sibling differentiation is incomplete.

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

Usage Guidelines2/5

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

There is no when-to-use guidance and no mention of alternatives, despite a sibling (get_orthologous_group) covering the conceptually adjacent task. The agent must infer that this tool is for pairwise orthologs per protein from the purpose statement alone.

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

Deploy Server