Compoid MCP

Compoid_create_record

Create a new Compoid record and submit it to a community for review.

Required:
    community_id: community slug (e.g. 'physics' - browse
        https://www.compoid.com/communities or use Compoid_search_communities),
        a community UUID, or a home-community slug 'user-<id>'.
    file_upload: the file to attach. Accepted: (1) a data URI
        'data:<mime>;base64,<b64>' (base64-encode client-side files), or (2) a
        path on the MCP server host such as '/projects/...' (e.g. the path
        returned by Compoid_upload_file). Plain client-local paths are NOT
        accessible to the server.
    creators: non-empty list of author / AI-model names (e.g.
        ['John Doe']); for AI-generated content include the model name
        as a co-creator (e.g. ['Qwen']).
    keywords: non-empty list of tags (e.g. ['Compoid', 'MCP']) - records
        without keywords are hard to discover.

Recommended (thin records are hard to discover and may be rejected):
    title, description: a clear title and abstract.
    resource_type: one of analysis, image, video, audio, publication, document,
        software, project, dataset, presentation, workflow, tutorial, other -
        any other value is rejected with 400 'Not a valid value.' (when omitted
        it is inferred from the file MIME type).
    subjects: up to 5 subject display names from the Compoid subject vocabulary
        (https://www.compoid.com/subjects); invalid names cause a 400.
        "Artificial Intelligence" is always appended as a default subject.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`title`	No
`creators`	Yes
`keywords`	Yes
`subjects`	No
`references`	No
`description`	No
`file_upload`	Yes
`community_id`	Yes
`resource_type`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 16, 2026

removedInput schema / properties / keywords / default
```
Removed value: -null
```

changedInput schema / required

Previous value: -[
-  "community_id",
-  "file_upload",
-  "creators"
-]New value: +[
+  "community_id",
+  "file_upload",
+  "creators",
+  "keywords"
+]

Changed1 schema field changedSep 15, 2026

addedInput schema / properties / subjects

Added value: +{
+  "default": null,
+  "items": {
+    "type": "string"
+  },
+  "title": "Subjects",
+  "type": "array"
+}

First observedMar 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that records are submitted for review, may be rejected when thin, that invalid resource_type and subject values cause 400 errors, that resource_type is inferred from MIME type when omitted, and that 'Artificial Intelligence' is always appended as a default subject. It also clarifies the important server-side file path limitation.

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

Conciseness5/5

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

The description is long but tightly structured with a one-sentence purpose, clear Required/Recommended sections, and dense, high-value bullets. Every line adds operational detail needed to call the tool successfully, and the formatting makes the information easy to scan.

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

Completeness4/5

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

The description covers purpose, required and recommended fields, validation failure modes, file upload formats, community lookup, and subject vocabulary. Since an output schema exists, return-value documentation is not needed. The only meaningful completeness gap is the undocumented 'references' parameter and the absence of explicit guidance on when to use update instead of create.

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%, so the description must compensate, and it does so extensively for community_id, file_upload, creators, keywords, resource_type, and subjects, including exact allowed values and error behavior. The only gap is 'references', which is present in the schema but never explained in the description.

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?

The description opens with a specific verb and resource: 'Create a new Compoid record and submit it to a community for review.' This clearly distinguishes it from sibling tools like Compoid_create_community and Compoid_update_record, and the submission context adds useful precision.

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?

The description clearly separates 'Required' from 'Recommended' fields and warns that thin records may be rejected. It also references sibling tools for supporting tasks (Compoid_search_communities for community lookup and Compoid_upload_file for file paths). It does not explicitly state when to prefer Compoid_update_record for existing records, but 'Create a new' makes the primary use case unambiguous.

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

All Compoid MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.