Can be deployed unchanged to Amazon Bedrock AgentCore Runtime, using its port 8080 and /ping health-probe contract for agent hosting.
Uses a configurable OpenAI-compatible chat-completions endpoint as the rewriting engine, with settings for base URL, model, API key, timeout, retries, and extra request JSON.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Prose in, plain-language prose out. One service scores prose against the FAA standard for plain language and returns it rewritten to the bar. You choose the engine. Any tool that speaks HTTP or MCP can call it, and it runs anywhere a container runs. The image is public on GitHub's container registry, so the pull below needs no credentials.
docker run --rm -p 8080:8080 \
-e INFERENCE_BASE_URL=https://your-gateway.example/v1 \
-e INFERENCE_MODEL=your-model \
-e INFERENCE_API_KEY=$TOKEN \
ghcr.io/overlabbed-com/plain-language-desk:latest
curl -s localhost:8080/score -H 'Content-Type: application/json' \
-d '{"text":"It shall be noted that the aforementioned provisions are required."}'POST /score grades the text and returns findings with a number. It changes
nothing. POST /improve returns the prose rewritten to the bar:
curl -s localhost:8080/improve -H 'Content-Type: application/json' \
-d '{"text":"…","mode":"full","audience":"ship engineers"}'mode=minimal fixes the violations the scorer names, and nothing else.
mode=full rewrites for style. Both run the same loop: score, rewrite with
the findings as feedback, re-score. The loop is monotonic — the response
carries the best score seen — and stops at the bar, the round cap, or when a
rewrite stops improving.
Related MCP server: slop-guard
Variable | Meaning | Default |
| OpenAI-compatible chat-completions endpoint | none — |
| Model name the endpoint serves | none |
| Bearer key, if the endpoint wants one | empty |
| Raw JSON merged into each request body, for engine-specific kwargs | empty |
| Per-call timeout and retry count | 120 s / 2 |
| A ruleset bundle directory | the shipped FAA bundle |
| Pass bar | 80 (bundle value) |
| Default round cap for | 3 (request can set 1–5) |
| Set it and every path but | unset — open |
| Listen port | 8080 |
One process serves both. The HTTP API lives at /score, /improve,
/healthz, and /ping. The MCP surface lives at /mcp with the tools
score_prose and improve_prose — DSH, Claude Code, omp, pi, and any other
MCP client call it directly. No harness-specific code exists in the service.
The same container deploys to Amazon Bedrock AgentCore Runtime unchanged: it
listens on port 8080 (PORT overrides it), answers /ping for the runtime's
health probe, and speaks plain JSON over HTTP — no cloud software development
kit anywhere.
The standard is data, not code. A bundle is a directory: RULESET.md (the
standard), ruleset.json (identity, bar, version), the two rewrite prompts,
and golden/ fixtures with pinned scores that the test suite replays. The
FAA bundle (faa-plain-language@1.0.0, from FAA Order 1000.36A and the federal
plain-language handbook) ships inside the package. Point RULESET_PATH at a
work-tuned bundle to run a different standard — a new bundle, not a fork.
Every response reports ruleset (id@version) and the bar that scored the
text. Code blocks, tables, and front matter never cost points: the scorer
strips machine-necessary formatting before it reads a word.
The container image is the deliverable, so its posture is checked, not promised — CI fails the build if any proof fails:
The runtime image has no shell; docker run … sh refuses.
It runs as a fixed non-root user with all capabilities dropped and a read-only root filesystem; the health check and a full score call pass under exactly that posture.
Both base images are pinned by digest; dependencies install from the package metadata, with no build tools in the final image.
Every build ships a software bill of materials, and the scanner fails on critical or high findings.
Port and health-check path env-configurable (PORT, /ping compatible) —
the AgentCore Runtime contract, and any kubelet or load balancer probe, out
of the box.
No secrets live in layers: configuration arrives at runtime by environment, and nothing in the image reads it at build time.
The digest pins age by design: refresh them deliberately — rebuild, scan, re-pin — in one commit.
The deterministic scorer is the DSH writing-standard scorer (WPS/1.1,
2026-10-31), vendored byte-identical and pinned by sha256 in the parity test.
Its rule table and the FAA citations live in the bundle's RULESET.md. The
scorer decides every score; the engine only rewrites.
python3 -m venv .venv && .venv/bin/pip install -e '.[dev]'
.venv/bin/python -m pytest tests -q
.venv/bin/python -m plain_language_desk # serve on :8080deploy/k8s/ ships a kustomize tree — Deployment, Service, ServiceAccount,
ConfigMap, and a deny-by-default NetworkPolicy — mirroring the homelab
log-triage pattern. kustomize build deploy/k8s | kubectl apply -f - after
setting INFERENCE_BASE_URL/INFERENCE_MODEL in configmap.yaml. CI
publishes the image to ghcr.io/overlabbed-com/plain-language-desk on every
merge to main (pin by digest in production).
This server cannot be deployed
Score and rewrite AI-assisted prose while preserving names, numbers, quotes, links, and facts.
Scores whether a page reads as AI-generated and names the tells to fix.
Score academic and professional writing against published criteria with three reference models.
Sentence-by-sentence analysis of a prose draft: a score for every sentence and every handoff.