io.github.dfch/biz-dfch-asdste100mcp
OfficialClick 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., "@io.github.dfch/biz-dfch-asdste100mcp Find the approved STE alternative for 'begin'."
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.
biz.dfch.AsdSte100Mcp
An MCP server for the ASD-STE100 (Simplified Technical English) Issue 9 standard.
ASD-STE100: Copyright by (c) ASD.
I am in no way affiliated with ASD. ASD does not endorse my work.
Table of Contents
Related MCP server: mcp-docmost
Authentication
This server exposes only read-only lookup tools and resources over
vocabulary and rules data that is bundled with the package; there is
nothing to authenticate against. No API keys, tokens, or credentials are
required or supported in either stdio or sse transport mode. If you
expose the sse transport beyond localhost, secure it at the network
layer (e.g. a reverse proxy) rather than expecting the server to
authenticate requests itself.
Tools
Vocabulary
Tool | Description |
| Search for a term by exact name (case-insensitive) in the ASD-STE100 Issue 9 vocabulary. Return approved/rejected status, part of speech, STE examples, and approved alternatives. Use this first when you know the exact word. Use |
| Search for multiple terms by exact name (case-insensitive) in a single call. Returns one |
| Search the vocabulary using a regular expression pattern. Return all entries whose term matches. Use it to find all words with a common prefix or pattern (e.g. ^de or .*tion$). Paginated ( |
| Search for a term with sequence-matching (Python difflib.get_close_matches). Results may not be obvious — use when |
| Return all vocabulary entries. Only use when you need to process the full vocabulary. Use |
| Return the total number of entries in the vocabulary. Use instead of |
| Search for vocabulary entries that are WordNet synonyms of a word, via the |
Rules
Tool | Description |
| Search for rules in the ruleset by exact id (case-insensitive), e.g. |
| Search rules using a regular expression matched against the rule |
| Full-text search across every text a rule carries (section, category, name, summary, and all content blocks: text, notes, examples, technical noun/verb lists). Optionally restrict to specific content types. Paginated ( |
| Search for rules by exact section name (case-insensitive), e.g. |
| Search for rules by exact category name (case-insensitive), e.g. |
| Return content items across rules, optionally scoped by id/section/category and filtered by content type. Paginated ( |
| Return a lightweight, per-rule overview (id, type, section, category, name, optional summary, and content counts/flags) without shipping every content item. |
| Return the distinct (section, category) pairs as a table-of-contents outline, optionally scoped to one section. |
Resources
Read-only resources let a client browse or attach ruleset data directly (e.g. via an "@mention" or resource picker), without going through a tool call.
Resource URI | Description |
| Table-of-contents outline of the ruleset: the distinct (section, category) pairs, each with the ids they contain. Mirrors the |
| A single rule/recommendation/information item by exact id (case-insensitive), e.g. |
| Installed version numbers of the MCP server itself and its three data-backing libraries: |
Installation
pip install biz-dfch-asdste100mcpOr with uv:
uv add biz-dfch-asdste100mcpUsage
MCP Inspector
If you want to test the MCP server without a tool like OpenCode, you can do this with MCP Inspector.
MCP Inspector is part of the mcp[cli] package. When you install this project with --extra dev you can use MCP Inspector.
NOTE: The examples below use bunx instead of npx to launch MCP Inspector; npx has not been tested.
stdio (Claude Desktop, OpenCode, and other MCP hosts)
asdste100-mcpRun MCP Inspector against the server over stdio:
bunx @modelcontextprotocol/inspector uv run --frozen --directory . asdste100-mcp
NOTE: Sometimes, the MCP Inspector cannot connect to the MCP server via stdio. Use the sse option (see below) instead.
SSE / network
asdste100-mcp --transport sse --host localhost --port 8000NOTE: You do not have to supply the option --port to the MCP server. The default value of port is 8000.
Start the server, then connect MCP Inspector to it — these are two separate commands, run in two separate terminals:
# terminal 1: start the server
uvx --from . asdste100-mcp -t sse# terminal 2: launch the inspector and connect it to the running server
bunx @modelcontextprotocol/inspector

Options
Option | Env var | Default | Description |
|
|
| Transport mode: |
|
|
| Bind address (SSE only) |
|
|
| TCP port (SSE only) |
| — | auto-discovered | Path to a |
|
| (empty) | Path to a vocabulary file ( |
|
| (empty) | Path to a rules file (a single JSON array); repeatable |
Vocabulary configuration
Env var | Default | Description |
| (empty) | Colon-separated paths to additional vocabulary files |
|
| Load the built-in ASD-STE100 Issue 9 vocabulary |
|
| Also load the technical words vocabulary |
Rules configuration
Env var | Default | Description |
| (empty) | Colon-separated paths to additional rules files (each a single JSON array) |
|
| Load the built-in ASD-STE100 Issue 9 ruleset |
Add to OpenCode
To add the ASD-STE100 (Simplified Technical English) MCP server to your OpenCode configuration:
Open your OpenCode config file (typically
~/.config/opencode/opencode.jsonor~/.config/opencode/opencode.jsonc)Add the following configuration to the
mcpsection (and use it viastdio):
"asdste100": {
"type": "local",
"enabled": true,
"command": ["uvx", "--from", "biz-dfch-asdste100mcp", "asdste100-mcp"]
}Save the file and restart OpenCode
This enables OpenCode to access ASD-STE100 vocabulary and rules lookups for technical writing and documentation compliance.
Development
Install dev dependencies
uv sync --all-extrasRun linters
uv run --frozen ruff format --check
uv run --frozen ruff check
uv run --frozen pylint $(git ls-files '*.py')Run tests
uv run --frozen python -m unittest discover -v -s tests -t . -p "test_*.py"Related Projects
This server is part of the ASD-STE100 tooling family:
biz.dfch.AsdSte100Vocab — the ASD-STE100 Issue 9 vocabulary library
biz.dfch.AsdSte100Rules — the ASD-STE100 Issue 9 ruleset library
biz.dfch.AsdSte100Nlp — WordNet-based synonym lookup for ASD-STE100 words
biz.dfch.AsdSte100Lookup — an interactive CLI to look up words and rules
biz.dfch.AsdSte100Mcp — this repo: an MCP server exposing vocabulary and rules lookup tools
Make a Release
1. Make sure all tests pass
Before releasing, make sure the CI pipeline is green on the dev branch:
uv run --frozen ruff format --check
uv run --frozen ruff check
uv run --frozen pylint $(git ls-files '*.py')
uv run --frozen python -m unittest discover -v -s tests -t . -p "test_*.py"2. Increase the version
Update the version in pyproject.toml:
version = "x.y.z"3. Commit and push to dev
git add pyproject.toml CHANGELOG.md
git commit -m "chore: bump version to vx.y.z"
git push origin dev4. Merge dev into main
git checkout main
git merge dev
git push origin main5. Create and push a version tag
export VERSION=x.y.z
git tag v${VERSION}
git push origin v${VERSION}Pushing the tag triggers the publish.yml workflow, which will:
Build the sdist and wheel.
Publish to TestPyPI (environment
testpypi).Publish to PyPI (environment
pypi), only if TestPyPI succeeded.Publish to the MCP Registry (
publish-to-mcp-registryjob) — requires the new version to be live on PyPI first.Create a GitHub Release with auto-generated notes and the distribution artifacts attached.
Then switch back to dev to continue work:
git checkout devConfigure Trusted Publishing
The workflow uses OIDC Trusted Publishing — no API tokens or secrets are needed.
GitHub: create environments
Go to your repo → Settings → Environments and create two environments:
Environment | Recommended protection |
| None required |
| Add a required reviewer to prevent accidental production releases |
TestPyPI
Log in at test.pypi.org → Your account → Publishing → Add a new pending publisher:
Field | Value |
PyPI project name |
|
Owner |
|
Repository |
|
Workflow name |
|
Environment |
|
PyPI
Log in at pypi.org → Your account → Publishing → Add a new pending publisher:
Field | Value |
PyPI project name |
|
Owner |
|
Repository |
|
Workflow name |
|
Environment |
|
MCP Registry Publishing
The publish-to-mcp-registry job uses GitHub OIDC authentication and does not require additional setup — it will automatically publish to the official MCP Registry once the package is live on PyPI.
Verify your server is registered:
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.dfch/biz-dfch-asdste100mcp"License
Available Tools
15 toolsrules_by_categoryARead-only
Search for rules in the ruleset by exact category name (case-insensitive).
Use rules_toc first if you do not know the exact category names.
Parameters
category:
The category name to search for, e.g. "Technical nouns".
Returns
list[Rule] A (possibly empty) list of matching rules.
Inputs: category (required). Returns: result
rules_by_sectionARead-only
Search for rules in the ruleset by exact section name (case-insensitive).
Use rules_toc first if you do not know the exact section names.
Parameters
section:
The section name to search for, e.g. "Words".
Returns
list[Rule] A (possibly empty) list of matching rules.
Inputs: section (required). Returns: result
rules_examplesARead-only
Return content items across rules, optionally scoped and filtered.
Parameters
id_:
When given, only consider the rule with this exact id
(case-insensitive).
section:
When given, only consider rules in this exact section
(case-insensitive).
category:
When given, only consider rules in this exact category
(case-insensitive).
kind:
When given, only return content items of this type (e.g.
"ste_example").
max_results:
The maximum number of matching content items to return (default 25).
offset:
The number of matching content items to skip before returning
results, for pagination (default 0).
Returns
RulesExamplesResult
results holds the (possibly empty) page of matching content
items, in document order, after applying offset and
max_results. total is the full match count before
pagination, and truncated tells the caller whether more
content items exist beyond this page. Unfiltered, the ruleset
can hold well over a thousand content items, so pagination
matters here even though the ruleset itself only has a few
dozen rules.
Inputs: id_, kind, offset, section, +2 more. Returns: A single page of a `rules_examples` result, with pagination metadata. Unfiltere…
rules_findARead-only
Search for rules in the ruleset by exact id.
Use this first when you know the exact rule/recommendation id. Use
rules_match or rules_search if this tool returns no items.
Parameters
id_:
The rule/recommendation id to search for (e.g. "R1.1" or
"GR-8"), matched case-insensitively.
Returns
list[Rule] A (possibly empty) list of matching rules.
Inputs: id_ (required). Returns: result
rules_matchARead-only
Search for rules in the ruleset using a regular expression.
The pattern is matched (case-insensitively) against both the name
and the summary of each rule. Use rules_search instead if you
need to search the full content of every rule (notes, examples,
technical noun/verb lists, ...).
Parameters
pattern: The regular expression pattern to search for.
Returns
list[Rule] A (possibly empty) list of matching rules.
Inputs: pattern (required). Returns: result
rules_overviewARead-only
Return a lightweight, per-rule overview of the ruleset.
Use this for a cheap, low-token summary of what rules exist before
drilling into rules_find or rules_examples for a specific rule;
each result carries only the rule's id, type, section, category,
name, and (optionally) summary, plus counts/flags about its content
items rather than the content items themselves.
Parameters
section:
When given, only consider rules in this exact section
(case-insensitive).
category:
When given, only consider rules in this exact category
(case-insensitive).
type_:
When given, only consider rules of this exact type (e.g.
"rule", to exclude recommendations and informational
blocks).
brief:
When True (default), omit the summary to keep the payload
small. When False, include the full summary.
Returns
list[RuleOverview] One overview per matching rule, in the ruleset's current order (natural id order by default).
Inputs: brief, type_, section, category. Returns: result
rules_searchARead-only
Full-text search for rules using a regular expression.
Unlike rules_match, which only looks at name and summary,
this searches every text a rule carries: section, category,
name, summary, and the data of every content item --
i.e. explanatory text, notes, STE/non-STE examples, technical
noun/verb lists, and so on. Useful for finding "what rule governs
passive voice" or "where does STE100 mention abbreviations", without
knowing the section/category/id upfront.
Parameters
pattern:
The regular expression pattern to search for (case-insensitive).
content_types:
When given, only the data of content items whose type is in
this list is searched (section, category, name, and
summary are always searched regardless). Use this to narrow
the search to, e.g., only note or ste_example content.
max_results:
The maximum number of matching rules to return (default 25).
offset:
The number of matching rules to skip before returning results,
for pagination (default 0).
Returns
SearchResult
results holds the (possibly empty) page of matching rules,
in document order, after applying offset and max_results.
total is the full match count before pagination, and
truncated tells the caller whether more matches exist beyond
this page -- i.e. whether a reached max_results means "that's
all of them" or "call again with a higher offset".
Inputs: pattern (required), offset, max_results, content_types. Returns: A single page of a `rules_search` result, with pagination metadata. See `PagedR…
rules_tocARead-only
Return the distinct (section, category) pairs, in first-seen order.
Gives a table-of-contents style outline of the ruleset's structure,
without any per-rule detail; useful to see which sections and
categories exist before drilling into rules_overview,
rules_by_section, or rules_by_category for a specific one.
Parameters
section: When given, only consider rules in this exact section (case-insensitive).
Returns
list[TocEntry]
One entry per distinct (section, category) pair, in first-seen
document order, where ids lists the ids of every
rule/recommendation/information item in that (section,
category), in document order.
Inputs: section. Returns: result
word_countARead-only
Return the total number of entries in the vocabulary.
Use instead of word_list when you only need the count.
Returns
int The number of entries in the vocabulary.
Inputs: no named parameters. Returns: result
word_findARead-only
Search for a term by exact name (case-insensitive) in the ASD-STE100 Issue 9 vocabulary.
Return approved/rejected status, part of speech,
STE examples, and approved alternatives. Use this first when you know
the exact word. Use word_match with a wildcard if this tool
returns no items.
Parameters
term: The word or phrase to look up exactly.
Returns
list[Word] A (possibly empty) list of matching vocabulary entries.
Inputs: term (required). Returns: result
word_find_manyARead-only
Search for multiple terms by exact name (case-insensitive) in the ASD-STE100 Issue 9 vocabulary in a single call.
Equivalent to calling word_find once per term, but avoids one
tool round-trip per term. Each input term gets its own entry in the
result, holding 0, 1, or more matching vocabulary entries — an
unknown or misspelled term simply yields an empty results list for
that entry rather than shrinking the overall result.
Parameters
terms: The words or phrases to look up exactly.
Returns
list[WordFindEntry]
One entry per input term, in the same order as terms, each
holding the term and its (possibly empty) list of matching
vocabulary entries.
Inputs: terms (required). Returns: result
word_fuzzyARead-only
Search for a term with sequence-matching (Python difflib.get_close_matches).
Results may not be obvious — use when find returns nothing and you want suggestions.
Parameters
term: The word or phrase to search for approximately.
Returns
list[Word] A (possibly empty) list of similar vocabulary entries.
Inputs: term (required). Returns: result
word_listARead-only
Return all vocabulary entries.
Only use when you need to process the full vocabulary. Use word_count instead if you only need the total. This operation is expensive and returns a large number of entries -- the vocabulary holds thousands of them.
Parameters
max_results: The maximum number of vocabulary entries to return (default 25). offset: The number of vocabulary entries to skip before returning results, for pagination (default 0).
Returns
WordResult
results holds the (possibly empty) page of vocabulary entries
after applying offset and max_results. total is the
full entry count before pagination, and truncated tells the
caller whether more entries exist beyond this page.
Inputs: offset, max_results. Returns: A single page of a `word_list`/`word_match` result, with pagination metadata. T…
word_matchARead-only
Search the vocabulary using a regular expression pattern.
Return all entries whose term matches. Use it to find all words with a common prefix or pattern (e.g. ^de or .*tion$). A broad pattern can match a large part of the vocabulary, so results are paginated.
Parameters
term:
A regular-expression pattern (e.g. "util.*").
max_results:
The maximum number of matching vocabulary entries to return
(default 25).
offset:
The number of matching vocabulary entries to skip before
returning results, for pagination (default 0).
Returns
WordResult
results holds the (possibly empty) page of matching
vocabulary entries after applying offset and max_results.
total is the full match count before pagination, and
truncated tells the caller whether more matches exist beyond
this page.
Inputs: term (required), offset, max_results. Returns: A single page of a `word_list`/`word_match` result, with pagination metadata. T…
word_synonymARead-only
Search for vocabulary entries that are WordNet synonyms of a word (via
the biz-dfch-asdste100nlp library's Nlp class).
Every WordNet synset for term is collected and its lemma names are
cross-referenced, case-insensitively, against the vocabulary's entries
by name — the same scope as word_find/word_match/word_fuzzy
(approved and rejected entries both included). term itself is
excluded from the result. Use this to find approved alternatives for a
non-STE word.
Parameters
term: The word to search synonyms for.
Returns
list[Word]
A deduplicated, alphabetically sorted list of matching vocabulary
entries. Empty if term has no WordNet synsets (out-of-
vocabulary) or none of its synonyms are present in the vocabulary.
Inputs: term (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
Each tool has a clearly distinct purpose: word_* tools cover exact, batch, regex, fuzzy, synonym lookup, count, and list; rules_* tools cover id, section, category, full-text, overview, examples, and TOC. The few adjacent tools (word_find vs word_find_many, rules_match vs rules_search) are explicitly differentiated in their descriptions.
All 15 tools follow a consistent snake_case verb_noun pattern with clear word_ and rules_ prefixes. The domain of each tool is immediately obvious from its name.
15 tools is well within the ideal range for a reference server covering both a vocabulary and a ruleset. Each tool serves a distinct lookup or navigation purpose, so none feel redundant.
The tool surface provides comprehensive read-only coverage: vocabulary count, list, exact/batch/fuzzy/regex/synonym search, and rules TOC, overview, find by id/category/section, match, full-text search, and examples. There are no obvious dead ends or missing operations for the stated purpose.
Maintenance
Related MCP Connectors
MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader.
MCP server for Translation Services
An MCP server that provides Javelin Standalone Guardrails
MCP server for Speech-to-Text
Related MCP Servers
- AlicenseCqualityDmaintenanceAn MCP server that provides text conversion, formatting, and analysis functions, which can be directly integrated into the development workflow.432Apache 2.0
- AlicenseAqualityDmaintenanceAn MCP server for the Docmost documentation platform that enables managing pages, spaces, and comments through natural language. It supports content search, page exports, and revision history tracking within the Docmost workspace.131MIT
- AlicenseBqualityDmaintenanceAn MCP server for reading, editing, and validating Microsoft Word documents with specialized support for track changes, comments, and footnotes. It enables structural auditing, heading extraction, and precise OOXML-level document manipulation through natural language tools.101001,057 PyPI69MIT
- FlicenseNot gradedqualityDmaintenanceA professional MCP server for analyzing content against the official Microsoft Writing Style Guide, enabling style, grammar, terminology, and accessibility checks via AI tools like VS Code and GitHub Copilot.1-