A
licenseB
qualityD
maintenanceMakes local markdown documentation files automatically available to AI assistants through MCP, enabling them to search and read organized documentation folders without manual file registration.
1
MIT
writulos-mcp
Officialby writulos
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@writulos-mcpGenerate markdown documentation for auth.js"
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.
writulos-mcp
Official MCP server for Writulos Scribe — generate markdown documentation for your code inside Cursor, Claude Desktop, and any MCP-compatible AI agent.
Installation
No install needed. Run directly with npx:
npx writulos-mcpOr install globally:
npm install -g writulos-mcpRelated MCP server: Functional Requirements MCP Server
Setup in Cursor
Add this to .cursor/mcp.json in your project root:
{
"mcpServers": {
"writulos": {
"command": "npx",
"args": ["-y", "writulos-mcp"],
"env": {
"WRITULOS_API_KEY": "writ_YOUR_API_KEY"
}
}
}
}Restart Cursor. Then in the AI chat, ask:
Document all the files in this project using writulosThe generated docs come back in the chat — ask Cursor to save them wherever you
keep documentation. The server itself only writes a run log to
docs/writulos.log (set WRITULOS_OUTPUT_DIR to move it), recording each run
and how many generations you have left this month.
Setup in Claude Code, Claude Desktop and other clients
Use the same command, args and env as the Cursor config above. Whichever
way the client adds the server, give it WRITULOS_API_KEY: without the key the
server still starts, and every tool call answers with where to get one.
Usage and limits
Each file documented uses one generation from your Writulos plan's monthly allowance, the same allowance the dashboard and the GitHub Action draw on. When it runs out, the tools say so and when it resets.
Tools
generate_docs
Generate markdown documentation for a single code file.
Inputs:
code(required) — the source codefilename(optional) — e.g.auth.jscontext(optional) — extra context about the file
generate_docs_batch
Generate markdown documentation for up to 20 files in one request.
Inputs:
files(required) — array of{ code, filename?, context? }objects
Requirements
Node.js 18+
A Writulos Scribe API key from scribe.writulos.com/dashboard/api-keys
Source and issues
This repository is a copy of the server, updated on every release. Report bugs and ask questions in its issues.
License
MIT
Available Tools
2 toolsgenerate_docsGenerate docs for a fileA
Generate markdown documentation for a single code file using Writulos. Uses one generation from the account's monthly allowance.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | The source code to document. | |
| context | No | Optional extra context about the file or project. | |
| filename | No | The filename, e.g. auth.js |
TDQS
A3.8/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover safety (readOnlyHint=false, destructiveHint=false, non-idempotent, openWorld), and the description adds a quota-consumption behavior not derivable from annotations: each call spends one of the account's monthly generations. It stops short of stating auth needs or what happens on failure.
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?
Two short sentences, zero waste, with the core action front-loaded and the cost caveat immediately after. Nothing extraneous.
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?
There is no output schema, but the description makes clear the return is markdown documentation, and it covers the quota side effect. It is complete enough to invoke correctly, though it could mention whether the markdown is returned inline or written somewhere.
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 100%, so all three parameters (code, context, filename) are already documented in the schema. The description adds no syntax, format, or constraint detail beyond noting the subject is a single file, which is the expected baseline when the schema does the heavy lifting.
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?
States a specific verb (Generate), resource (markdown documentation), and scope (a single code file), which implicitly distinguishes it from the batch sibling. It does not name generate_docs_batch explicitly, so an agent must infer the contrast from the word 'single'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The quota note ('Uses one generation from the account's monthly allowance') gives a real cost consideration for choosing this tool, but there is no explicit when-to-use guidance or routing to generate_docs_batch for multi-file work.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
generate_docs_batchGenerate docs for several filesA
Generate markdown documentation for multiple code files in one request (up to 20 files). Uses one generation per file from the account's monthly allowance.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| files | Yes | Array of files to document. Maximum 20 per request. |
TDQS
A3.7/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (non-destructive, non-idempotent, open-world), so the bar is lower; the description adds genuinely new behavioral context by disclosing that each file consumes one generation from the account's monthly allowance — a quota/cost trait not present in the annotations.
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?
Two short sentences, both front-loaded, with no filler: the capability and its limit come first, the quota consequence second.
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?
No output schema exists, so the description should explain what comes back for a batch (e.g. per-file results, ordering, or partial-failure behavior), and it does not. Quota and cap are covered, but the return shape and failure semantics are missing.
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 description coverage is 100% and there is only one top-level parameter, so the schema already documents files, code, context, and filename. The description's 'up to 20 files' merely restates the schema's maxItems: 20 rather than adding new parameter meaning.
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?
States a specific verb and resource ('Generate markdown documentation for multiple code files in one request') and the batch scope plus 20-file cap make it distinguishable from the single-file sibling generate_docs, even though the sibling is not named explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'in one request' implies the batch use case versus the single-file sibling, and the 20-file cap is stated, but there is no explicit when-to-use/when-not guidance or pointer to generate_docs for single files.
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.
2 tool updates
v1.0.3- First observed
generate_docs - First observed
generate_docs_batch
TDQS
A3.9/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: generate_docs handles a single file while generate_docs_batch handles multiple files (up to 20). The boundary between them is unambiguous, so an agent can select correctly.
Naming Consistency5/5
Both names follow a consistent snake_case verb_noun pattern (generate_docs), with the batch variant distinguished by a clean suffix. No mixed conventions or stylistic drift.
Tool Count3/5
Two tools is on the thin side for the stated domain. While each tool earns its place, the surface feels minimal and could likely support additional operations like allowance checks or retrieval.
Completeness3/5
The server covers the core documentation-generation action, but there are notable gaps: no way to check remaining monthly allowance, list previously generated docs, or retrieve/read generated output. Agents will hit dead ends for anything beyond fire-and-forget generation.
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Convert PDF documents to Markdown for AI agents through an authenticated remote MCP server.
Publish and share access-controlled Markdown documents from any MCP-enabled AI tool.
Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables developers to generate structured software documentation including user stories, requirements, technical specifications, and more using AI-powered prompts via the MCP protocol.8-
- FlicenseNot gradedqualityDmaintenanceMCP server that exposes one or more documentation folders (Markdown, MDX, TXT) to AI agents, enabling listing, reading, and searching of documentation files.-
- AlicenseNot gradedqualityAmaintenanceMCP server that studies a folder of code repositories, generates markdown documentation (architecture, interfaces, activity), and serves answers over MCP with live ripgrep search and file reads so AI assistants can query codebases and their relationships.10 npmMIT