Skip to main content
Glama

search_references

Read-onlyIdempotent

Find design references in the saved corpus by filtering host, owner, or tags or using a free-text query against the taxonomy. Returns score, matched fields, and credit.

Instructions

Find patterns previously kept with capture_reference — call it before rebuilding something already grabbed, or to recall 'that hero from Linear'. host, owner, and tags filters compose with AND; the free-text query expands recognized pattern intent through Raven's controlled vocabulary, then matches case-insensitively against note, app, tags, bound taxonomy ids, and selector. Every result carries a score and a 'why' naming the matched fields and any alias that connected the query to the record. Ordering is deterministic. Returns stored JSON records. Every result carries a display object holding the credit line, the source URL, and image_path — the PNG on disk for records captured with html, so results can be shown as pictures rather than style maps (the tool returns the path, never the bytes). Browsing does not hand back the other site's markup. A result reports html_available and html_truncated but omits the html itself; pass include_html:true to receive it, which is a deliberate step because that markup is the site's own authored expression rather than a measurement of it. Everything needed to LOOK at a pattern and to translate it onto this project's tokens — the picture, the selector, the rect, the computed styles — is in the default result. Show the credit whenever you show the pattern: this corpus holds other people's design work, Raven does not own it, and a third-party result also carries a notice saying so. Use these as references to build your own implementation, not as work to republish. Corrupt records are named in skipped[] instead of failing the call. It does not rank against live code and does not fetch the source site.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hostNoOnly references grabbed from this host, e.g. 'linear.app'
tagsNoOnly references carrying ALL of these tags
ownerNoOnly the user's own product, or only third-party sites
queryNoFree text expanded through the pattern taxonomy and matched against note, app, tags, bound taxonomy ids, and selector; omit to list everything passing the filters
include_htmlNoReturn each record's captured markup verbatim. Off by default: browsing a corpus of other people's work should not hand back their markup as a side effect of looking at it. Ask for it when you are actually reading the structure.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Addedv2.5.1

TDQS

A4.7/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing deterministic ordering, return shape, skipped[] for corrupt records, that it never fetches the source site, that markup is omitted by default, and that results carry display/credit info. These are important behavioral traits not visible anywhere in the structured metadata.

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?

The description is front-loaded with the key use call and gives strong behavioral guidance, but it is long and contains some redundancy — for example, the return payload details are stated across overlapping sentences ('Every result carries a score and a why' / 'Every result carries a display object'). Still, nearly all content earns its place.

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?

With no output schema, the description must carry the return-value explanation, and it does so thoroughly: score, why, display object, image_path, html_available, html_truncated, skipped[] for corrupt records, and the no-fetch/no-ranking guarantee. An agent has enough context to call the tool and interpret results correctly in most situations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds real semantics on top: filters compose with AND, the free-text query expands through Raven's controlled vocabulary, include_html is off by default because of authorship concerns, and corrupt records go to skipped[]. This goes well beyond the schema's individual property descriptions.

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: 'Find patterns previously kept with capture_reference,' and gives concrete use cases like recalling 'that hero from Linear.' It clearly distinguishes its scope from capture_reference and other knowledge tools by tying results to previously captured references.

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?

It gives explicit context for when to call the tool: before rebuilding something already captured, or when recalling a specific known pattern. It also explains when to use include_html versus the default behavior. However, it does not explicitly name sibling alternatives such as search_knowledge and say when to choose those instead, so it stops short of full exclusionary guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rhinocap/raven-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server