flowforge-mcp

flowforge_api_reference

Read-onlyIdempotent

Search the bundled FlowForge External API spec by keyword or resource group, or read one endpoint's exact parameters and request schema before writing code or making API requests.

Instructions

Search the FlowForge External API (all 160 endpoints) or read one endpoint's exact contract. Offline - reads the bundled OpenAPI spec.

Use before flowforge_api_request and before writing code that calls FlowForge, so field names and required params are right the first time.

Modes:

no args -> resource-group index with endpoint counts.
query and/or group -> matching endpoints (method, path, summary).
method + path -> full description: path/query params and the $ref-resolved request body. In schemas a trailing * on a property name means required.

Returns: JSON. Base URL and auth are included in the index for code generation.

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": {
      "params": "<params>"
    },
    "name": "flowforge_api_reference"
  }
}

Input Schema

Name	Required	Description	Default
`params`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses that the tool is offline and reads a bundled OpenAPI spec (so no network or auth is needed for the lookup itself) and that base URL and auth details are surfaced in the index for code generation. It also explains a non-obvious schema convention — a trailing '*' on a property name means required — which annotations and schema 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.

Conciseness5/5

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

Front-loaded purpose sentence, then a use-before rule, then a compact bulleted mode map, then a short returns note. Every line carries actionable information with no restating of the name or title.

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?

For a read-only reference lookup with an output schema present, the description supplies everything needed: purpose, invocation modes, the '*' required-marker convention, and confirmation that results are JSON. No ambiguity remains about how to call it correctly.

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?

The description explains how query and group combine for search, how method+path unlock full endpoint mode, and gives a concrete path example ('/calls/abc123/events'), which is meaning beyond the schema. However, it says nothing about 'limit' (including the 160 cap) or 'include_response_schema', leaving two of six parameters to the schema alone.

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 names a specific verb and resource ('Search the FlowForge External API... or read one endpoint's exact contract') and explicitly scopes it to the 160 bundled endpoints. It is immediately distinguishable from the sibling flowforge_api_request, which actually executes calls, and from the domain-specific CRUD siblings.

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?

It states an explicit ordering rule: 'Use before flowforge_api_request and before writing code that calls FlowForge.' The three modes (no args, query/group, method+path) map conditions to outputs, so the agent knows exactly which argument combination selects which behavior.

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

Deploy Server