S1000D Writer MCP
It lets an LLM author and maintain S1000D content from structured drafts without writing XML, with verification, controlled fixes, numbering, CSDB writing, manual conversion, comments, and translation segment handling.
Build one S1000D data module (
descript,proced,process,fault) or publication module (pm) from a structured draft and allocation rules; returns XML, file name, code, verification, fixes, ledger, and next ICN.Number DMCs/PMCs/ICNs via allocation rules and a ledger so the same
sourceIdkeeps the same DMC; pass the ledger back between calls.Verify XSD, BREX chain, references, and applicability when a product is provided; automatically apply only
exactfixes with exactly one candidate, up tomaxFixRounds, and return remaining fixes with candidates.Convert an experiential manual JSON into a publication module, one data module per topic, a glossary module, applicability, and ICNs for assets; report what cannot be represented in
notRepresented.Apply selected fixes to an existing data module only when a selection matches a candidate; reject values outside candidates or ranges and re-verify.
Create comment data modules (
comment.xsd) with references, type, priority, paragraphs, originator, and sender; default sequence number is the next free one in the CSDB.Extract translatable sentences from an existing data module with stable ids, XPaths, placeholders, and
skeletonHash; apply translations back while keeping the same DMC and detectingskeleton-mismatch.Use CSDB folders via
csdbDirs,S1000D_CSDB_DIR, or the config file; write only whenwrite: true, avoid overwrites by default, and control invalid-XSD writes withallowInvalid.Run over stdio by default or Streamable HTTP with
--http, configurable host, port, path, and allowed host/origin checks.Return draft/rule mistakes as
error.code: "input-error"withpathanddetailinstead ofisError.
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., "@S1000D Writer MCP Build a proced data module from this draft and verify it against the BREX"
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.
@shuji-bonji/s1000d-writer-mcp
English | 日本語
An MCP server that lets an LLM create S1000D® data modules without writing XML. The LLM passes a structured draft and numbering rules; the server builds the XML, verifies it against the XSD, the BREX and the references, and applies automatically only the fixes that have exactly one candidate (exact). A fix with several candidates is applied only from a selection, and a value outside the candidates is never accepted. By default nothing is written.
This is a personal project and is not affiliated with ASD (Aerospace, Security and Defence Industries Association of Europe). S1000D® is a registered trademark of ASD.
The S1000D specification, XML schemas, default BREX and official samples are not included in any package or repository, because their terms of use do not grant redistribution. Obtain them froms1000d.org and point the S1000D_SPEC_DIR environment variable at the extracted folder.
What it does
Tool | Description |
| Builds a data module from one draft (descript, proced, process, fault or PM) and numbering rules. The DMC, ICN and issue come from the ledger ( |
| Converts an experiential manual ( |
| Applies the fixes you chose from the candidates in |
| Builds a comment data module ( |
| Takes the sentences a person reads out of a data module (titles, paragraphs, steps, warnings, table cells, figure captions) so they can be translated. Inline elements are replaced by |
| Puts translated sentences back into the data module they were taken from. The DMC stays the same and only the language changes. It stops with |
Write rules
Nothing is written by default. Only with
write: truedoes the server writeDMC-….XMLinto the first folder ofcsdbDirs(or the first ofS1000D_CSDB_DIR). With no destination it writes nothing and returns the reason (no-csdb-dir).A file with the same name is not overwritten (
write-conflict) unlessoverwrite: trueis passed.XML that violates the XSD is not written (
schema-invalid) unlessallowInvalid: trueis passed.schema-not-found(no XSD available) is not a violation; the file is written as unverified.With
write: true,convert_manualalso copies the original assets under their ICN file names.
What is fixed automatically
Only a fix whose confidence is exact and which has exactly one candidate is applied (for example, replacing a value when the BREX allows a single responsible company, or removing an element the BREX forbids). several (more than one candidate, or a value given as a range) and none are not applied and are returned in fixes[]. The user chooses, and the server never fixes with a value outside the candidates. Each applied fix is returned in appliedFixes[] with the values before and after.
Verification status (verification)
Every response carries the verification status of the XSD, the BREX and the references. A missing XSD is reported as schema-not-found and a skipped step as not-run; neither is valid. The server reports the result of verification only: it does not judge conformance to S1000D and does not interpret severity.
Input errors
A mistake in the draft or the numbering rules is returned not as isError but as error: { code: "input-error", path, detail }. path is the location of the mistake (for example /body[1] or /allocation/rules/infoCodeByKind/proced). Fix it and call again.
Related MCP server: AutoCAD MCP Pro
What it does not do
It does not accept XML written by an LLM. It builds only from a draft. The tools that take existing XML (
apply_fixes,extract_segments,apply_segments) do not change the structure of the document.It does not fix with a value outside the candidates. There is no entry point for writing a free value.
It does not skip verification. A built XML is always verified before it is returned.
It does not judge conformance to S1000D or interpret severity. Read the violations in
s1000d-verify-mcpand the explanation of BREX rules ins1000d-brex-mcp.It does not translate. It only takes sentences out and puts them back. The LLM or a person translates.
It does not create illustrations or judge Simplified Technical English (STE). For an illustration it only allocates an ICN and inserts the reference.
What a data module cannot represent, such as hotspot coordinates or part of
scopeRefsin an experiential manual, is reported innotRepresentedand never dropped silently.It does not create an ACT, CCT or PCT. Applicability relies on the
applicof the draft and an existing applicability repository. When a draft given tobuild_data_modulehas noapplic, the server does not build it and returnsinput-error(pathis/applic). The server does not decide applicability, so give at leastapplic.displayText(convert_manualusesdefaultApplic, by default the display text "All", for topics withoutscopeRefs).
Configuration
Environment variable | Meaning |
| The folder where you extracted the S1000D distribution you obtained. The XSDs ( |
| The folder holding the project's data modules. Several can be given, separated by |
You can also give folders with the tool argument csdbDirs (the first one is the write destination). When the argument is given, only those folders are used; S1000D_CSDB_DIR and csdbDirs in the config file are not used (they are not added together). Folders that do not exist are skipped and listed in _notes of the response. The first folder may not exist yet; it is created with write: true.
Config file (when environment variables are not passed, such as a Claude Desktop plugin)
When S1000D_SPEC_DIR / S1000D_CSDB_DIR are not set, the server reads the config file ~/.config/s1000d-stack/config.json (under XDG_CONFIG_HOME if set; the location can be changed with S1000D_CONFIG). Claude Desktop does not pass environment variables to a server installed as a plugin, so write the settings here in that case.
{
"specDir": "/path/to/s1000d/issue-7",
"csdbDirs": ["/path/to/your/csdb"]
}Environment variables take precedence when they are set. The config file is read again on every call.
Example configuration for Claude Desktop / Claude Code
{
"mcpServers": {
"s1000d-writer": {
"command": "npx",
"args": ["-y", "@shuji-bonji/s1000d-writer-mcp"],
"env": {
"S1000D_SPEC_DIR": "/path/to/s1000d/issue-7",
"S1000D_CSDB_DIR": "/path/to/your/csdb"
}
}
}
}Running over HTTP (embedding in a product)
The default is stdio. With --http the server starts over Streamable HTTP.
npx -y @shuji-bonji/s1000d-writer-mcp --http # http://127.0.0.1:3000/mcp
npx -y @shuji-bonji/s1000d-writer-mcp --http --port 3102 --path /writerArgument | Default | Meaning |
|
| Address to bind to |
|
| Port; |
|
| Path of the MCP endpoint. |
| (see below) | Host names allowed in the |
| (see below) | Host names allowed in the |
When --host is a loopback address, Host and Origin are limited to localhost names (DNS rebinding protection). When bound to any other address they are not checked, so put the server behind the product's reverse proxy or authentication. Because this server can write files, do not expose it without authentication.
How it works
All building, verification, fixing, comment and segment code lives in the shared library @shuji-bonji/s1000d-core; this server holds only the interpretation of arguments, the shape of the responses and the conversion from a manual to drafts (src/convert/). The input schemas import the definitions of core's draft.schema.json. The conversion is also available as @shuji-bonji/s1000d-writer-mcp/convert.
Development
npm install
npm test # runs on self-made test data only (tests/fixtures/)
npm run test:spec # uses the distribution you obtained (location given by S1000D_SPEC_DIR; default ../../specs/s1000d/issue-7)
npm run build && S1000D_SPEC_DIR=/path/to/issue-7 S1000D_CSDB_DIR=/path/to/csdb npm start # start over stdioLicense
MIT. S1000D® is a registered trademark of ASD. This software is not affiliated with ASD and does not include the specification, schemas or official samples.
Available Tools
6 toolsapply_fixesA
Apply fixes to an existing data module. Each selection copies the location and ONE candidate of a fix that s1000d-verify-mcp suggest_fixes (or this server) returned: { location, action, target?, value? }. The server computes the fix candidates again and applies a selection only if it matches one of them; a value outside the candidates (or outside a range / pattern candidate) is not applied and comes back in rejected[] with the reason. "provide" candidates change the product, not the document: pass them as "product". The result is verified again. Returns xml, applied[], rejected[], verification, the fixes that remain. Writes only when write is true (a path is overwritten in place; xml is written under its own file name in the first CSDB folder).
Inputs: selections (required), xml, path, write, +5 more.
apply_segmentsA
Put translated sentences back into the data module they were taken from. The output has the same DMC with only the language changed (issueInfo too if given). It stops with error.code "skeleton-mismatch" when the data module changed since extract_segments (skeletonHash). A segment whose id is unknown, duplicated, or whose {n} placeholders do not match is not applied and is listed in unapplied[] (the original sentence stays). The result is verified. Writes only when write is true.
Inputs: language (required), segments (required), skeletonHash (required), xml, +7 more.
build_data_moduleA
Build ONE S1000D data module (descript / proced / process / fault) or publication module (pm) from a structured draft and number it from the allocation rules. You give titles, paragraphs, steps, tables, figures and references as a tree; the server writes the XML (you never write XML, DMCs, ICNs or the BREX reference). The XML is verified (XSD, BREX along the brexDmRef chain, references; applicability too when a product is given); fixes the server is certain about (confidence "exact") are applied automatically and verified again, up to maxFixRounds times. Returns xml, fileName, dmCode (pmCode for a pm), verification, appliedFixes[] (what was changed automatically), fixes[] (what remains: candidates to choose from), the updated ledger and the next ICN number. Writes into the CSDB only when write is true. A malformed draft comes back as error.code "input-error" with the path of the problem.
Inputs: draft (required), allocation (required), write, product, +7 more.
convert_manualA
Convert an experiential operation manual (@shuji-bonji/experiential-manual-model JSON) into S1000D: one publication module, one data module per topic (description → descript, procedure → proced, troubleshooting → fault, screenFlow → process plus one proced per screen), a glossary data module, applicability from the scopes, and ICNs for the assets. Every data module goes through the same flow as build_data_module (build, verify, automatic exact fixes, verify again); references between the data modules are resolved against the CSDB plus the data modules built in this call. Returns dataModules[], publicationModule, assets[] (assetId → ICN and the original file; with write: true the originals are copied under the ICN file name), the ledger, a summary of verification states and notRepresented (what the draft format cannot express). Nothing is written unless write is true.
Inputs: allocation (required), securityClassification (required), write, manual, +17 more.
create_commentA
Build a comment data module (comment.xsd): a remark about data modules, publication modules, DMLs or DDNs, with the type (q / i / r), the priority code (cp01–cp99), paragraphs, the originator and the sender. The enumerations are written as given and not interpreted. The sequence number defaults to the next free one in the CSDB. The XML is verified (comment.xsd, BREX). Returns xml, fileName, commentCode, verification, fixes[]. Writes only when write is true.
Inputs: language (required), originator (required), paragraphs (required), commentType (required), +18 more.
extract_segmentsA
Take the sentences that a person reads out of a data module so they can be translated: titles, paragraphs, step texts, warnings / cautions / notes, table cells and figure captions. Each segment has a stable id, its XPath, a context hint and the text, with inline elements (emphasis, references …) replaced by {1}, {2} placeholders that must stay in the translation. Attribute values, DMCs, ICNs, applicability expressions and ids are never offered. Also returns the skeletonHash to pass to apply_segments. The server does not translate and does not score translations.
Inputs: xml, path, include, maxSegments.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct operation: drafting a DM/PM, bulk conversion of an external manual format, applying verifier-suggested fixes, building a comment module, and the tightly paired extract/apply translation tools. The only overlap is build_data_module versus convert_manual, since the latter reuses the former's build/verify flow, but the input domains (structured draft vs experiential-manual JSON) are clearly separated in the descriptions.
All six names follow a strict snake_case verb_noun pattern (build_, convert_, apply_, create_, extract_, apply_). The prefixes are semantically accurate: build/create for new artifacts, apply_ for mutating operations, extract_ for read/export.
Six tools is well-scoped for an S1000D authoring server, with no filler: authoring, bulk conversion, remediation, commenting, and a clear extract/apply pair for translation. Nothing appears redundant or missing that would require a single tool to bolt on unrelated modes.
The toolset covers creation, fixes, commenting, and translation round-trips, but there is no read/list/get operation to inspect or retrieve existing data modules from the CSDB, which is a real dead end (e.g. you cannot list candidates before extracting or fixing). There is also no DML/DDN authoring or delete/retire operation, so the lifecycle is only partially covered.
Maintenance
Related MCP Connectors
Compiles structured specs into SCORM 1.2/2004 e-learning packages. 47 tools, quality gate, no LLM.
Manage SysML2 projects; check, evaluate, verify, query, document and diagram models.
Convert, lint and generate LLM tool schemas for OpenAI, Anthropic, Gemini and MCP
30+ deterministic dev and delivery tools: linting, metrics, diagrams, model advice, AI-text checks.
Related MCP Servers
- AlicenseAqualityBmaintenanceProvides LLM agents with a toolset for reviewing S1000D technical publications, including XML schema validation, cross-reference and applicability checks, skeleton generation, and AI-suggested fixes.1MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to draft, inspect, and validate CAD drawings through a large typed tool catalog, driving either a live desktop CAD seat over COM or a headless ezdxf engine on any platform. It covers ISO GD&T and dimension-tolerance checks plus P&ID, mechanical, and architectural sheet generation, with selectable tool packs and a low-token discovery mode.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to create, edit, validate, and read back production-grade CAD drawings — including P&ID sheets, mechanical parts and assemblies, and architectural floor plans with measured areas and schedules — through a single typed tool contract that runs either live via COM on Windows or headlessly via ezdxf anywhere. It also supports standards-aware dimensioning, ISO GD&T and tolerance checks, takeoff workbooks, and drawing understanding, diffing, and critique.-
- AlicenseAqualityBmaintenanceEnables an LLM to read S1000D BREX data modules and check data modules against them, reporting allowed elements, values, SNS code meanings, and permitted illustration formats. Also returns each rule violation with its XPath location, actual value, rule ID, and severity, following the BREX reference chain layer by layer.5319 npmMIT