FlyTrap MCP Server

Official

by FlyTrap-QA

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Get screen graph

get_screen_graph

Read-only

Retrieve the screen graph from a FlyTrap crawl run to see reached screens and tap edges, helping answer navigation and dead-end questions.

Instructions

Screens the crawler reached in the selected run and the tap edges between them (from -> to via element). Useful for "how do I get to X" and dead-end questions. Requires FLYTRAP_API_KEY.

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": {
      "project_id": "<project_id>"
    },
    "name": "get_screen_graph"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	Yes	FlyTrap project id (from list_projects)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.4Nov 7, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, so safety is covered and the bar is lower. The description adds two genuinely useful facts: the FLYTRAP_API_KEY requirement and the edge structure returned. It says nothing about graph size, truncation, or pagination for a potentially large crawl graph, and 'the selected run' is never explained.

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?

Three short sentences, front-loaded with what the tool returns, then the use cases, then the auth prerequisite. Every sentence carries information; only 'useful for' phrasing is slightly softer than a direct statement of intent.

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 read-only, single-parameter tool with no output schema, the description does sketch the return shape (screens plus directed tap edges), which is the important part. However, the 'selected run' scoping has no corresponding parameter and no explanation, leaving an agent unsure whether the graph reflects the latest build or a prior one.

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?

Only one parameter and schema coverage is 100%, so the baseline is 3. The description adds scoping context beyond the schema by framing the result as belonging to a 'selected run' and a project's crawler, though it never explains how that run is selected, which is the one ambiguity the schema cannot resolve.

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 resource and its shape: the screens reached in a crawl run plus the tap edges between them, with the edge model spelled out as '(from -> to via element)'. That is far more than a restatement of the name, and no sibling tool deals in navigation graphs, so it is distinguishable even though no sibling is named.

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 concrete question shapes the tool answers: 'how do I get to X' and dead-end questions. That is real when-to-use guidance tied to user intent, but it offers no exclusions or explicit alternative (e.g., what to use for screen contents rather than reachability).

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