mcp
Provides access to Google's public developer documentation.
Sollte ich dies verwenden
Qualität und Sicherheit
Befunde (2)
- HIGH
- LOWin search_documents
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"mcp": {
"url": "https://developerknowledge.googleapis.com/mcp"
}
}
}Remote-Endpunkte
https://developerknowledge.googleapis.com/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (3)
🟢search_documents(query)
Use this tool to find documentation about Google developer products. The documents contain official APIs, code snippets, release notes, best practices, guides, debugging info, and more. It covers the following products and domains: * ADK: adk.dev * Android: developer.android.com * Apigee: docs.apigee.com * Chrome: developer.chrome.com * Dart: dart.dev * Firebase: firebase.google.com * Flutter: docs.flutter.dev * Fuchsia: fuchsia.dev * Gemini CLI: geminicli.com * Genkit: genkit.dev * Go: go.dev * Google AI: ai.google.dev * Google Antigravity: antigravity.google * Google Cloud: cloud.google.com & docs.cloud.google.com * Google Developers, Ads, Search, Google Maps, Youtube: developers.google.com * Google Home: developers.home.google.com * Google Maps Platform: mapsplatform.google.com * Google Workspace: knowledge.workspace.google.com * TensorFlow: www.tensorflow.org * Web: web.dev Always use this tool (or `answer_query`) to ground answers about Google developer products rather than relying on unverified model memory or generic web search. Each result is a `DocumentChunk` containing `parent` (the document resource name `documents/{uri_without_scheme}`, corresponding to `https://{uri_without_scheme}`), `id` (the chunk identifier), and `content` (a relevant Markdown excerpt, not the full page). Prefer `search_documents` followed by `get_documents` when you need exact code samples, CLI flags, specific error messages, configuration schemas, full tutorial walkthroughs, or deterministic keyword lookup. Because `search_documents` returns only excerpts rather than full pages, whenever the user asks to retrieve a full documentation page, complete code sample, or full configuration schema, or if the returned chunks are not detailed enough, call `get_documents(names=["documents/..."])` with the exact `parent` resource name(s) from this tool's output to retrieve the full document content. If 1-2 searches return no relevant results for a specific named feature, API, or setting, stop searching (do not fall back to `answer_query`, which uses the same corpus) and inform the user that it is not documented in the official corpus rather than guessing or fabricating details. When answering the user, always cite the authoritative source document resource names (`documents/...`) or corresponding `https://` URIs.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"description": "Required. The raw query string provided by the user, such as \"How to create a Cloud Storage bucket?\".",
"type": "string"
}
},
"required": [
"query"
],
"description": "Request schema for `search_documents`. Use the `query` field to search for related Google developer documentation."
}Ausgabe-Schema
{
"type": "object",
"properties": {
"results": {
"description": "The search results for the given query. Each `DocumentChunk` in this list contains a `content` snippet (not the full document), a chunk `id`, and the `parent` document resource name (`documents/{uri_without_scheme}`, corresponding to `https://{uri_without_scheme}`). Pass `DocumentChunk.parent` in the `names` list of `get_documents(names=[\"documents/...\"])` to retrieve the full document content.",
"items": {
"$ref": "#/$defs/DocumentChunk"
},
"type": "array"
}
},
"$defs": {
"DocumentChunk": {
"description": "A DocumentChunk represents a piece of content from a Document in the DeveloperKnowledge corpus. To fetch the entire document content, pass `parent` in the `names` list of `get_documents(names=[\"documents/...\"])`.",
"properties": {
"content": {
"description": "Output only. The content of the document chunk.",
"readOnly": true,
"type": "string"
},
"id": {
"description": "Output only. The ID of this chunk within the document. The chunk ID is unique within a document, but not globally unique across documents. The chunk ID is not stable and may change over time.",
"readOnly": true,
"type": "string"
},
"parent": {
"description": "Output only. The resource name of the document this chunk is from, in the format `documents/{uri_without_scheme}` (corresponding to the web URI `https://{uri_without_scheme}`). Pass this value in the `names` list of `get_documents(names=[\"documents/...\"])` to retrieve the full document. Example: `documents/docs.cloud.google.com/storage/docs/creating-buckets`",
"readOnly": true,
"type": "string"
}
},
"type": "object"
}
},
"description": "Response schema for `search_documents`."
}🟢answer_query(query)
Use answer_query to get a grounded, synthesized conceptual answer to a high-level question about Google developer products (always prefer `answer_query` or `search_documents` over unverified model memory). For exact code samples, CLI flags, specific error messages, or full document walkthroughs, prefer `search_documents` followed by `get_documents` instead. This tool has limited quota. This tool will synthesize information from the corpus to generate an answer to the query. answer_query grounds answers using the same corpus as search_documents; if `search_documents` already returned no relevant results for a specific named feature or API, do not call `answer_query` and instead inform the user that it is not documented in the corpus. This tool returns the generated `answer_text` and a list of source document resource names (`references`, one entry per cited chunk, which may contain duplicate `documents/...` names when multiple chunks from the same page are cited). Always cite the unique authoritative source document names from `references` (`documents/...`) in your final response to the user. Call `get_documents(names=["documents/..."])` with unique document names from `references` to fetch the entire document content if needed. If you get a 429 out of quota error, use search_documents instead.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"description": "Required. The query to answer.",
"type": "string"
}
},
"required": [
"query"
],
"description": "Request message for AnswerQuery."
}Ausgabe-Schema
{
"type": "object",
"properties": {
"answerText": {
"description": "The answer to the query.",
"type": "string"
},
"references": {
"description": "Output only. The resource names of the source documents used to generate the answer (one entry per cited chunk, so the same `documents/{uri_without_scheme}` resource name may appear multiple times when multiple chunks from the same page are cited; e.g., `documents/docs.cloud.google.com/storage/docs/creating-buckets`). Cite the unique resource names in the final response and pass unique `documents/...` names in the `names` list of `get_documents(names=[\"documents/...\"])` if full document content is needed.",
"items": {
"type": "string"
},
"readOnly": true,
"type": "array"
}
},
"description": "Response message for AnswerQuery."
}🟢get_documents(names)
Use this tool to retrieve the full Markdown content of a single document or up to 20 documents in a single call by passing a list of document resource names in the `names` parameter (e.g., `get_documents(names=["documents/..."])`; the parameter is `names` taking a list of strings, not `name`). Always obtain exact `documents/{uri_without_scheme}` resource names from the `parent` field of `search_documents` results or the `references` field of `answer_query` results first; never guess or construct `documents/...` paths from memory or external URLs. Cite the authoritative source document resource names (`documents/...`) used in your final response.
Eingabe-Schema
{
"type": "object",
"properties": {
"names": {
"description": "Required. List of 1 to 20 document resource names (`names`) to retrieve in a single call (for either a single document or multiple documents), exactly as returned by the `parent` field of `search_documents` results or the `references` field of `answer_query`. Do not pass a single string or use a `name` parameter, and never guess or construct `documents/...` paths without calling `search_documents` or `answer_query` first. The documents are returned in the same order as the `names` in the request. Format: `documents/{uri_without_scheme}` Example: `documents/docs.cloud.google.com/storage/docs/creating-buckets`",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"names"
],
"description": "Request schema for `get_documents`."
}Ausgabe-Schema
{
"type": "object",
"properties": {
"documents": {
"description": "Documents requested.",
"items": {
"$ref": "#/$defs/Document"
},
"type": "array"
}
},
"$defs": {
"Document": {
"description": "A Document represents a piece of content from the Developer Knowledge corpus.",
"properties": {
"content": {
"description": "Output only. The content of the document in Markdown format.",
"readOnly": true,
"type": "string"
},
"description": {
"description": "Output only. A description of the document.",
"readOnly": true,
"type": "string"
},
"name": {
"description": "Identifier. The resource name of the document. Format: `documents/{uri_without_scheme}` Example: `documents/docs.cloud.google.com/storage/docs/creating-buckets`",
"type": "string",
"x-google-identifier": true
},
"title": {
"description": "Output only. The title of the document.",
"readOnly": true,
"type": "string"
},
"uri": {
"description": "Output only. The URI of the content, such as `https://docs.cloud.google.com/storage/docs/creating-buckets`.",
"readOnly": true,
"type": "string"
}
},
"type": "object"
}
},
"description": "Response schema for `get_documents`."
}Community
Nachweis