Skip to content
MCP server

S1000D Reader (S1000D Stack)

MCP server that reads S1000D data and publication modules as structure with applicability

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI
Runs
Locally
Version
0.13.0
Listing updated
3 days ago

About S1000D Reader (S1000D Stack)

S1000D Reader (S1000D Stack) is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Raw S1000D XML is awkward for a model, so this server hands back the document as a tree: heading hierarchy, numbered steps, warnings, cautions, notes, illustrations (ICN), tables and the titles of reference targets. A publication module comes back as a table of contents with each dmRef and pmRef resolved to a file, title and issue.

Its main idea is applicability. Pass a product and each block is marked applicable, notApplicable or undetermined, where undetermined carries a reason and does not mean the block is irrelevant; omitNotApplicable can drop the irrelevant blocks. A describe_applicability tool lists the attributes, conditions and products defined in the ACT, CCT and PCT, and evaluates nothing. Every response includes a verification field, running XSD validation by default or the full BREX chain when asked.

For large modules, an outline mode returns headings, step numbers and subtree sizes so the document can be surveyed first. The S1000D specification and schemas are not bundled; set S1000D_SPEC_DIR to a copy from s1000d.org. It is a personal project, not affiliated with ASD.

Install

Run in a terminal

claude mcp add s1000d-reader-mcp -- npx -y @shuji-bonji/s1000d-reader-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "s1000d-reader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@shuji-bonji/s1000d-reader-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "s1000d-reader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@shuji-bonji/s1000d-reader-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "s1000d-reader-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@shuji-bonji/s1000d-reader-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "s1000d-reader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@shuji-bonji/s1000d-reader-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "s1000d-reader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@shuji-bonji/s1000d-reader-mcp"
      ]
    }
  }
}

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

list_data_modules
Lists data modules in a CSDB with DMC, title, issue, language, schema and applicability text
read_data_module
Reads one data module as structure, optionally marking applicability for a product
read_publication_module
Reads a publication module as a table of contents
resolve_reference
Resolves a DMC, PMC or ICN to a file in the CSDB
describe_applicability
Returns the applicability vocabulary from the ACT, CCT and PCT
read_icn_metadata
Reads an ICN metadata file

What it does

Structured module reading
Returns headings, steps, warnings, tables and illustrations as a tree.
Applicability filtering
Marks blocks applicable, notApplicable or undetermined for a given product.
Outline mode
Surveys a large data module before reading its body.
Reference resolution
Resolves a DMC, PMC or ICN to a file in the CSDB.
Image metadata
Reads ICN metadata files including keywords and security classification.
Verification status
Each response says how far the document was verified.

Good for

  • Summarise a maintenance procedure without parsing XML
  • List data modules in a CSDB by system or information code
  • Show only the steps that apply to one product variant
  • Resolve the file behind an illustration reference

Pricing

Open source

Prices change. Check shuji-bonji.github.io before you buy.

S1000D Reader (S1000D Stack) FAQ

What does undetermined mean?

The server could not evaluate applicability, for example because the product lacks an attribute. It is not the same as not applicable.

How is verification handled?

By default XSD validation runs; verify full also checks the BREX chain.

Is the S1000D specification included?

No. Get it from s1000d.org and set S1000D_SPEC_DIR.

Does it edit data modules?

The README describes only reading tools.

Is S1000D Reader (S1000D Stack) free?

Yes. S1000D Reader (S1000D Stack) is open source, so you can use and self-host it for free.

How do I add S1000D Reader (S1000D Stack) to Claude Code?

Run this command in your terminal: claude mcp add s1000d-reader-mcp -- npx -y @shuji-bonji/s1000d-reader-mcp

What are the best alternatives to S1000D Reader (S1000D Stack)?

The closest alternatives to S1000D Reader (S1000D Stack) are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to S1000D Reader (S1000D Stack)

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools