What can you do with this server?

This MCP server provides tools to crawl, index, search, and retrieve documentation, with optional AI summaries. Key capabilities: * Crawl: Crawl documentation sites with configurable scope, concurrency, delays, page limits, and content size to build a local searchable index. * Search: Perform keyword/phrase searches on the index, returning results with URL, title, excerpt, and relevance score (up to 20 results). * Page retrieval: Fetch complete content of a specific documentation page by URL. * Status check: View crawler configuration and whether an index exists. * HTTP API: Expose search and health endpoints; optionally generate AI-powered summaries via AWS Bedrock. * MCP integration: Serve as an MCP server for AI clients (e.g., Claude Desktop), exposing tools for crawl, search, get page, and status. * Configuration: Controlled via config.json or environment variables.

How do I use MCP Documentation Crawler?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Documentation Crawler search the Plant Applications docs for 'production unit'" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP Documentation Crawler

by codecracker2020

Overview Schema Related Servers Score Discussions

JavaScript

Local

MCP Documentation Crawler

A local, configurable Model Context Protocol server that crawls a documentation site, stores a local index, and gives Claude (or another MCP client) search and page-retrieval tools.

The default configuration targets GE Vernova Proficy Plant Applications 2025 documentation. It only follows links within the configured domain and path prefix.

Install and crawl

git clone https://github.com/codecracker2020/mcp-server-crawler.git
cd mcp-server-crawler
npm install
cp config.example.json config.json
npm run crawl -- --config=config.json
npm run search -- --config=config.json "production unit"

The generated local index is data/index.json (ignored by Git). Re-run npm run crawl to refresh it.

Related MCP server: rock-mcp

HTTP API for other applications

Start the API after crawling:

npm run serve -- --config=config.json

It listens on http://127.0.0.1:3100 by default and exposes:

curl "http://127.0.0.1:3100/health"
curl "http://127.0.0.1:3100/search?q=releasing%20a%20route&limit=5"
curl "http://127.0.0.1:3100/search?q=releasing%20a%20route&summarize=true"

GET /search returns JSON with the query, index timestamp, and matching url, title, excerpt, and score fields. Add summarize=true to include a Claude summary grounded only in those matching excerpts. This uses AWS Bedrock's normal credential chain (for example AWS_PROFILE, access keys, or an IAM role) and the configured bedrockRegion and bedrockModelId; it makes a billed Bedrock request. Use apiHost, apiPort, and apiCorsOrigin to configure the server. Keep the default loopback host unless another machine truly needs access; if you expose it on a network, set MCP_CRAWLER_API_KEY and send it as the X-API-Key request header.

Claude Desktop / Claude Code / VS Code configuration

Add this server configuration to the MCP settings used by your client, adjusting the absolute paths:

{
  "mcpServers": {
    "plant-applications-docs": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-server-crawler/src/server.js", "--config=/absolute/path/to/mcp-server-crawler/config.json"]
    }
  }
}

For Claude Code, the equivalent command is:

claude mcp add --transport stdio plant-applications-docs -- node /absolute/path/to/mcp-server-crawler/src/server.js --config=/absolute/path/to/mcp-server-crawler/config.json

After restarting or reloading the client, it exposes four tools: crawl_documentation, search_documentation, get_documentation_page, and crawler_status.

Configuration

Copy config.example.json to config.json and change any field. startUrl, allowedDomains, and urlPathPrefix form the crawl boundary. The server also accepts every major setting as an environment variable, which is useful for VS Code settings or CI:

JSON field	Environment variable
`startUrl`	`MCP_CRAWLER_START_URL`
`allowedDomains`	`MCP_CRAWLER_ALLOWED_DOMAINS` (comma-separated)
`urlPathPrefix`	`MCP_CRAWLER_URL_PATH_PREFIX`
`maxPages`	`MCP_CRAWLER_MAX_PAGES`
`concurrency`	`MCP_CRAWLER_CONCURRENCY`
`requestDelayMs`	`MCP_CRAWLER_REQUEST_DELAY_MS`
`maxContentChars`	`MCP_CRAWLER_MAX_CONTENT_CHARS`
`dataDirectory`	`MCP_CRAWLER_DATA_DIR`
`apiHost`	`MCP_CRAWLER_API_HOST`
`apiPort`	`MCP_CRAWLER_API_PORT`
`apiCorsOrigin`	`MCP_CRAWLER_API_CORS_ORIGIN`
`apiKey`	`MCP_CRAWLER_API_KEY`
`bedrockRegion`	`MCP_CRAWLER_BEDROCK_REGION` (or `AWS_REGION`)
`bedrockModelId`	`MCP_CRAWLER_BEDROCK_MODEL_ID`
`bedrockMaxTokens`	`MCP_CRAWLER_BEDROCK_MAX_TOKENS`

Use the configuration conservatively and comply with the documentation site's terms and robots policy. The crawler deliberately ignores non-HTML pages and removes navigation, scripts, styles, and other page chrome before indexing.

Available Tools

4 tools

crawl_documentationA

Crawl the configured documentation site and save a local searchable index. Use refresh=false to reuse an existing index.

ParametersJSON Schema

Name	Required	Description	Default
`refresh`	No	Rebuild the index even when one already exists (default true).
`maxPages`	No	Optional per-run page limit, capped by configured maxPages.

TDQS

A4.2/5.0

Behavior3/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It states that the tool crawls a site and saves an index, and implies that refresh controls rebuilding. However, it does not disclose potential side effects such as network load, duration, or whether the old index is destroyed on refresh.

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?

The description is two sentences, front-loaded with the core purpose, followed by a concise usage hint. Every word contributes meaning; there is no fluff or repetition.

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?

Given the tool's moderate complexity and lack of output schema, the description is nearly sufficient. It explains what the tool does and a key usage parameter. It could mention that the resulting index is used by sibling search tools, but that is implied by the name and sibling context.

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 description coverage is 100%, so the baseline is 3. The description adds value by explaining the refresh parameter's behavior ('reuse an existing index'), which goes beyond the schema's simple description. The maxPages parameter is left to the schema, but the overall benefit justifies a 4.

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 clearly states the action (crawl), the resource (configured documentation site), and the outcome (save a local searchable index). This distinguishes it from sibling tools like crawler_status, search_documentation, and get_documentation_page, which perform different functions.

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?

The description provides a specific usage hint: 'Use refresh=false to reuse an existing index.' This gives clear context for when to use the parameter. However, it does not explicitly mention alternatives or when not to use this tool, though the purpose inherently separates it from siblings.

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

crawler_statusA

Show active crawler configuration and whether a local documentation index exists.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states a read-only 'Show' operation, which implies non-destructiveness. It also reveals the specific data points (configuration, index existence) that the tool reports, offering transparent expectations. However, it does not detail output format or any implicit limitations, but for a simple status tool this is adequate.

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?

The description is a single, focused sentence of about 15 words. It front-loads the verb and resource, contains no filler, and effectively communicates the core functionality. Every word 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?

Given the tool's simplicity (no parameters, no output schema, no annotations), the description is complete enough for an agent to understand what the tool does. It covers the key aspects: showing configuration and index existence. The sibling context further clarifies its role, and no additional details are necessary for basic invocation.

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?

The tool has zero parameters, so schema coverage is trivially 100%. The description adds meaning by explaining what the tool reports, which is not strictly about parameters but provides context for interpreting the tool's output. Baseline for 0 params is 4, and the description meets that without needing to compensate for undocumented parameters.

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 clearly states the tool's function with a specific verb ('Show') and resource ('active crawler configuration' and 'whether a local documentation index exists'). It is distinct from sibling tools like crawl_documentation (action), search_documentation (search), and get_documentation_page (retrieve), making its purpose obvious.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or comparison to sibling tools. While the context of sibling names is given, the description itself offers no usage direction.

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

get_documentation_pageB

Retrieve a complete indexed documentation page by URL.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes

TDQS

B3.1/5.0

Behavior2/5

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

With no annotations provided, the description must disclose behavioral traits itself. It does not mention what happens if the URL is not indexed, what 'complete' means in terms of response size, whether the URL must be canonical, or any error conditions. The phrase 'by URL' hints at a direct lookup but lacks depth about side effects or limitations.

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?

The description is a single, concise sentence with no filler or redundant wording. It includes the core action and key parameter mechanism, making it easy to parse. There is no unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (one param), but the description omits essential context. Without an output schema, the description should clarify what the 'complete indexed documentation page' contains (e.g., HTML content, metadata, links), but it does not. It also gives no indication of how the response is structured or what errors might occur. The description is minimally viable but leaves significant gaps.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate. It only restates that a URL is used ('Retrieve ... by URL') without adding meaning beyond the schema's 'url' property with format 'uri'. It does not clarify what constitutes a valid documentation page URL, how the URL should be encoded, or whether it must match a previously crawled URL.

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 uses a specific verb ('Retrieve') and resource ('complete indexed documentation page'), and clearly identifies the input ('by URL'). This distinguishes it from sibling tools: crawl_documentation (creates the index), search_documentation (finds pages), and crawler_status (monitors crawling). It fully states what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites (e.g., the page must already be crawled/indexed), no exclusions, and no comparison to search_documentation. The only implied usage is 'have a URL, get the page,' but this is not enough to navigate among siblings.

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

search_documentationA

Search the locally crawled documentation index. Crawl first if no index is available.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes	Words or phrase to search for.

TDQS

A3.8/5.0

Behavior3/5

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

There are no annotations, so the description carries the burden. It implies a read-only search operation and hints at index availability, but does not explicitly state side effects, failure modes, or return behavior. The prerequisite helps but lacks full transparency.

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?

The description is two sentences, front-loaded with the primary purpose, and every word earns its place. It is appropriately sized for a simple tool.

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 simple search tool, the description covers purpose and a prerequisite, but lacks return format and behavior when no index is present. Given no output schema or annotations, more detail would be expected, but it is not entirely inadequate.

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

Parameters2/5

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

Schema coverage is only 50% (query described, limit not). The description does not add any parameter information beyond the schema. The 'limit' parameter remains unexplained, and the description does not compensate for the coverage gap.

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 uses a specific verb and resource: 'Search the locally crawled documentation index.' It clearly distinguishes from siblings like crawl_documentation and get_documentation_page by specifying the resource (index) and the action (search).

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?

The description provides a clear prerequisite: 'Crawl first if no index is available,' indicating when to use the crawler alternative. However, it does not explicitly mention when to use get_documentation_page or crawler_status, so it is not fully comprehensive.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.0Aug 11, 2026
- First observedcrawl_documentation
- First observedcrawler_status
- First observedget_documentation_page
- First observedsearch_documentation

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0

Disambiguation5/5

Each tool has a distinct purpose: status checking, crawling, searching, and page retrieval. No overlap or ambiguity exists between them.

Naming Consistency4/5

Most tools follow a clear verb_noun pattern (crawl_documentation, search_documentation, get_documentation_page), but crawler_status uses a noun_noun style. Still, the snake_case naming is consistent and readable.

Tool Count5/5

With exactly 4 tools, the set is well-scoped for a documentation crawler. Each tool serves a necessary function and the count is appropriate for the server's purpose.

Completeness4/5

The core workflow of crawling, searching, and fetching pages is covered. A minor gap is the lack of an explicit clear/delete index operation, but refresh=false in crawl_documentation mitigates this.

Maintenance

ActivityMaintained

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

forkast-mcp-docs A
io.github.ForkastPredict
MCP server for querying Forkast documentation
Documentation Access Search Developer Tools
42
opencode
io.github.doc2mcp
MCP server for opencode documentation, generated by doc2mcp.
Documentation Access Developer Tools
24
innovationlab
io.github.doc2mcp
MCP server for innovationlab documentation, generated by doc2mcp.
Documentation Access Developer Tools
24
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102

Related MCP Servers

MCP AI Docs
Documentation Access Search
cartek99
F
license
Not graded
quality
D
maintenance
An MCP server that provides indexed, searchable access to Anthropic Claude and Google Gemini documentation, with full-text search, page fetching, and section listing capabilities.
Updated 7 months ago (2026-01-23 07:08 UTC)
-
rock-mcp
Documentation Access Search RAG Systems
sethwebster
F
license
Not graded
quality
D
maintenance
Documentation crawler MCP server that crawls and indexes documentation sites so that any MCP-compatible AI can search, read, and expand on the content.
Updated 7 months ago (2026-02-21 20:41 UTC)
1
-
devdoc
Documentation Access RAG Systems Search
vision-release
A
license
Not graded
quality
C
maintenance
A documentation MCP server that crawls websites and Git repositories, stores them as Markdown, and provides tools to search and retrieve documentation for local LLMs and AI agents.
Updated 5 months ago (2026-04-10 16:44 UTC)
Apache 2.0
mcp-docs
Documentation Access Search RAG Systems
pgupta1795
A
license
Not graded
quality
D
maintenance
MCP server for documentation search that automatically indexes web documentation sites and provides semantic, full-text, or hybrid search capabilities.
Updated 8 months ago (2026-01-19 14:46 UTC)
14
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/codecracker2020/mcp-server-crawler'

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