Skip to main content
Glama
onshape-jamcp

onshape-jamcp

Call any Onshape API endpoint

onshape_api_request
Destructive

Call any Onshape REST endpoint directly to perform operations not covered by dedicated tools, passing HTTP method, API path, query parameters, and optional JSON body.

Instructions

Escape hatch: call any Onshape REST endpoint directly. Use it for things the dedicated tools do not cover. WARNING: this is the raw API - lengths are in METERS (no unit conversion), POST/DELETE can change or destroy data, and in read-only mode only GET is allowed. Large responses are truncated.

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": {
      "method": "<method>",
      "path": "<path>"
    },
    "name": "onshape_api_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoJSON request body for POST.
pathYesAPI path relative to /api/vNN, e.g. '/documents' or '/partstudios/d/<did>/w/<wid>/e/<eid>/featurespecs'. See the Onshape API Explorer: https://cad.onshape.com/glassworks/explorer
queryNoQuery-string parameters.
methodYesHTTP method.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: raw-API units in METERS with no conversion, POST/DELETE can change or destroy data, read-only mode restricts to GET, and large responses are truncated. The unit and truncation disclosures are not derivable from readOnlyHint/destructiveHint/openWorldHint and directly affect how an agent constructs calls and handles output.

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?

Front-loads the escape-hatch framing, then the usage rule, then a compact WARNING block. Four short sentences, each carrying distinct information, with no redundant restatement of the schema.

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?

Covers the essential hazards for a raw, destructive, arbitrary-endpoint tool, and an output schema exists so return values need not be described. Minor gaps remain, such as whether the tool surfaces HTTP status/error details or how truncation boundaries are reported.

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 100%, so path, method, query, body, and the API Explorer link are all documented in the schema itself. The description's meter warning adds useful meaning about body values, but otherwise adds little parameter-level detail beyond the schema.

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 action (call any Onshape REST endpoint directly) and explicitly positions itself as an 'escape hatch' relative to the dedicated sibling tools. An agent can immediately distinguish it from tools like get_document or list_features.

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?

Gives a clear selection rule: use it for things the dedicated tools do not cover, which implicitly routes covered operations to the named dedicated tools. It also states the read-only-mode constraint (only GET allowed), though it does not say explicitly 'prefer the dedicated tool when one exists'.

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