PCFHub

List PCF controls

list_components

Read-onlyIdempotent

Browse the PCFHub catalog by category, tag, author, control type, host or text, paged and sorted. Use it to enumerate or narrow the catalog; use search for a plain-language question about what a control should do, and get_component for one control in full. Filters take slugs, which list_taxonomy supplies. Nothing here fails on bad input: an unrecognised sort falls back to the default, and filters matching nothing return an empty page — so read total and sort from the result rather than assuming the filters applied.

Input Schema

Name	Required	Description
`host`	No	Where the control has to run. A control supporting both hosts matches either.
`page`	No	Defaults to 1.
`sort`	No	Defaults to relevance when there is a query, newest otherwise.
`tags`	No	Tag slugs, from list_taxonomy. A control must carry every tag given.
`query`	No	Words to match against names, taglines and descriptions.
`author`	No	An author slug, from list_taxonomy.
`category`	No	A category slug, from list_taxonomy.
`per_page`	No	Defaults to 24; at most 48.
`control_type`	No	field binds one column on a form; dataset renders a view; virtual is a React control; grid_customizer changes how an editable grid renders cells.

Output Schema

Name	Required	Description
`page`	Yes	The page returned.
`sort`	Yes	The sort actually applied, which is the default when none was given or the one given was not recognised.
`total`	Yes	Controls matching the filters, across every page.
`perPage`	Yes
`lastPage`	Yes	The highest page number for these filters.
`components`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 5, 2026

addedOutput schema / properties / components / items / properties / builtWith

Added value: +{
+  "description": "ai where an AI assistant wrote the code, ai-assisted where a person wrote it with one. Null where the author has not said.",
+  "enum": [
+    "ai",
+    "ai-assisted",
+    null
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / components / items / properties / supportLevel

Added value: +{
+  "description": "maintained, or reference: a worked example not maintained for production. Null where the author has not said.",
+  "enum": [
+    "maintained",
+    "reference",
+    null
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed3 schema fields changedSep 19, 2026

addedInput schema / properties / host

Added value: +{
+  "description": "Where the control has to run. A control supporting both hosts matches either.",
+  "enum": [
+    "canvas",
+    "model-driven"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / components / items / properties / hosts

Added value: +{
+  "description": "Where this control runs. Empty only where nobody has declared it.",
+  "items": {
+    "enum": [
+      "canvas",
+      "model-driven"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / properties / components / items / required

Previous value: -[
-  "slug",
-  "name",
-  "controlType",
-  "category",
-  "author",
-  "downloadCount",
-  "url"
-]New value: +[
+  "slug",
+  "name",
+  "controlType",
+  "hosts",
+  "category",
+  "author",
+  "downloadCount",
+  "url"
+]

Changed1 schema field changedSep 16, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "components": {
+      "items": {
+        "properties": {
+          "author": {
+            "description": "Author slug.",
+            "type": "string"
+          },
+          "category": {
+            "description": "Category slug.",
+            "type": "string"
+          },
+          "controlType": {
+            "enum": [
+              "field",
+              "dataset",
+              "virtual",
+              "grid_customizer"
+            ],
+            "type": "string"
+          },
+          "downloadCount": {
+            "type": "integer"
+          },
+          "latestVersion": {
+            "description": "Null where nothing has been released yet.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "name": {
+            "type": "string"
+          },
+          "slug": {
+            "description": "Pass to get_component.",
+            "type": "string"
+          },
+          "tagline": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "Absolute URL of the control's page.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "slug",
+          "name",
+          "controlType",
+          "category",
+          "author",
+          "downloadCount",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "lastPage": {
+      "description": "The highest page number for these filters.",
+      "type": "integer"
+    },
+    "page": {
+      "description": "The page returned.",
+      "type": "integer"
+    },
+    "perPage": {
+      "type": "integer"
+    },
+    "sort": {
+      "description": "The sort actually applied, which is the default when none was given or the one given was not recognised.",
+      "type": "string"
+    },
+    "total": {
+      "description": "Controls matching the filters, across every page.",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "page",
+    "perPage",
+    "lastPage",
+    "total",
+    "sort",
+    "components"
+  ],
+  "type": "object"
+}

First observedSep 13, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnly and idempotent, but the description adds substantial non-obvious behavior: bad input never fails, an unrecognised sort silently falls back to the default, and non-matching filters yield an empty page. It tells the agent to read `total` and `sort` from the result rather than assuming filters applied — exactly the kind of failure-mode disclosure structured fields cannot carry.

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?

Three tight sentences, front-loaded with the capability and followed by routing and caveats in priority order. Every sentence carries distinct information — scope, alternatives, and failure semantics — with no repetition of schema content.

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 an output schema present, return structure needn't be explained, yet the description still points at the meaningful result fields. Given nine optional filter parameters and read-only annotations, an agent has everything needed to call this correctly and interpret the response.

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?

Schema coverage is 100%, so the baseline is 3, and the description earns credit for adding the sort fallback rule ('relevance when there is a query, newest otherwise' is implied by the dynamic default) and the slug provenance from list_taxonomy. It does not add syntax beyond the schema's enum descriptions, so it stops short of a 5.

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 verb and resource — browse the PCFHub catalog — and enumerates the dimensions it can be narrowed by (category, tag, author, control type, host, text). It also explicitly distinguishes itself from the search and get_component siblings, so an agent can route without opening a schema.

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?

Gives explicit when-to-use ('enumerate or narrow the catalog') and names the two alternatives with the conditions that select them: search for plain-language questions, get_component for a single control in full. It also flags the prerequisite that filter values are slugs supplied by list_taxonomy.

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

All PCFHub tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?