Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_search

Find Figma nodes by name, stable key, or text without fetching the full tree; filter by node type, key prefix, or presence, and return compact records with paths and snippets.

Instructions

Find nodes by name, stable key or text without fetching the whole tree. Substring (default), regex or glob matching; filter by node type, key prefix, hasKey, or use no query with a filter. Returns compact node records with path, matched fields, a text snippet, build root and size. Read-only; maxNodes and maxResults are reported when hit.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "figma_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNosubstring
queryNoText to find; omit when filtering only by types/keyPrefix/hasKey
typesNoOnly these node types, e.g. ['TEXT','FRAME']
fieldsNoWhere the query may match
hasKeyNotrue = keyed nodes only; false = unkeyed only
fileKeyNoWhich connected Figma file to use: its fileKey (figma_whoami) or, when omitted, the only connected file. Required once more than one file is connected; figma_ping lists them.
maxNodesNo
keyPrefixNoOnly stable keys beginning with this prefix
maxResultsNo
rootNodeIdNoSubtree root; defaults to the current page
caseSensitiveNo
includeHiddenNoSearch hidden layers too

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.36.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it declares "Read-only" and discloses truncation behavior ("maxNodes and maxResults are reported when hit"). It also sketches the return shape (path, matched fields, text snippet, build root, size), though it does not mention permission/auth prerequisites beyond the fileKey selection handled in schema.

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?

Four tightly packed sentences with the primary capability front-loaded and no filler. The density is high but each clause carries distinct information about matching modes, filters, or output, so little is wasted.

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?

For a 12-parameter search tool with no annotations and no output schema, the description covers the essentials an agent needs: matching semantics, filter-only usage, return record shape, and truncation signaling. The gaps (case sensitivity default, hidden-layer handling, subtree rooting) are minor because the schema documents them directly.

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 67%, and most of what the description says about parameters (mode options, type filter, keyPrefix, hasKey, no-query filtering) simply restates what the schema already documents in its property descriptions. Undocumented or thinly documented parameters such as caseSensitive, includeHidden, and rootNodeId get no added meaning from the description, so it does not fully compensate for the coverage gap.

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?

Opens with a specific verb and resource ("Find nodes") and names the three match targets (name, stable key, text) plus the key efficiency benefit ("without fetching the whole tree"). It does not explicitly contrast with nearby siblings such as figma_search_design_system or figma_inspect, so the differentiation is conceptual rather than 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 clear operating context: substring is the default, regex and glob are available, and it explicitly covers the filter-only case ("use no query with a filter"), which is echoed by the query parameter's schema note. It stops short of stating when to prefer this over an alternative tool, so no exclusion guidance is present.

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