Eigenstyle MCP server
Commit Nov 11, 2026Analyzes writing fingerprints and manages a personal corpus to help AI agents check drafts for stylistic consistency.
Also known as qompassai/eigenstyle
- Stars
- 0
- Tools
- 8
- Downloads, 30 days
- —
- Latest version
- 1.0.4
- Last commit
- Nov 11, 2026
- License
- Apache-2.0
What is Eigenstyle MCP?
Eigenstyle analyzes writing fingerprints and manages a personal corpus to help AI agents check drafts for stylistic consistency. It exposes 8 tools, such as check_draft, get_exemplars, get_profile.
Summary generated from the project's README
About Eigenstyle MCP server
Eigenstyle provides a system for measuring and managing a personal writing fingerprint to ensure stylistic consistency in AI-generated text. It functions as an MCP server via stdio, allowing AI agents to analyze drafts against a specific user voice profile. The server uses a core Rust library to track metrics such as sentence-length distribution, punctuation rates, and function-word profiles. Users can manage their writing corpus through a terminal UI or a desktop GUI, which share a common data store.
Developers can use specific tools like check_draft to receive a verdict on whether a text is close to or drifting from their established style. The server includes capabilities to ingest new samples via text, file paths, or URLs, and can retrieve verbatim exemplar paragraphs through get_exemplars. To maintain accuracy, the system allows for explicit recomputation of the fingerprint with a dry-run preview to inspect changes before they are applied. It is designed for users who need a mathematical rather than intuitive approach to maintaining a consistent brand or personal voice.
What you can do with it
- 1Verify stylistic consistencyAsk an AI agent to check a new draft against your established writing fingerprint to see if it matches your voice.
- 2Retrieve stylistic examplesRequest specific paragraphs from your existing corpus that match a particular genre to use as drafting references.
Written from the project's README. Every use case is checked against a quote from it.
Eigenstyle MCP tools 8
Detected from the READMEcheck_draftget_exemplarsget_profileingest_samplelist_corpusrecompute_fingerprintbrandvoice-mcpbook-writer
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableqompassai/eigenstyle is public and reachablegithub.com/qompassai/eigenstyle ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-11github.com/qompassai/eigenstyle ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model8 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubeigenstyle — your voice profile as a tool
A Rust workspace that turns a measured writing fingerprint
(built 2026-10-11 in the matt-voice skill) into a living system: an
MCP server agents can call, a terminal UI, and a GPUI desktop GUI — all
over one core library, all fed by a corpus you keep adding to.
The fingerprint is measured, not vibes: sentence-length distribution, function-word profile, punctuation rates, parentheticals, hyphenated compounds, hedge/assertive balance, first-person rate — the same features, tokenizer, rounding, and leave-one-out band calibration as the skill's Python reference. A parity test suite proves the Rust engine reproduces the Python numbers on the seed corpus (features and bands identical; checker deltas on the held-out pieces match: JAS 1.196, Cureus 1.088, synthetic 1.253).
The three front-ends
| Front-end | Binary | Run it |
|---|---|---|
| MCP server (stdio) | eigenstyle |
cargo run --release -p eigenstyle (add --home <dir> to choose the store) |
| Terminal UI | eigenstyle-tui |
cargo run --release -p eigenstyle-tui |
| Desktop GUI | eigenstyle-gui |
cargo run --release -p eigenstyle-gui (Wayland session) |
All three share one store: $EIGENSTYLE_HOME, else
~/.local/share/eigenstyle/. First open seeds it from the skill's
corpus (6 pieces, 7,674 words), fingerprint, and readable profile.
MCP tools
| Tool | What it does |
|---|---|
check_draft |
Score a draft (text or file): verdict CLOSE / DRIFTING / OFF-VOICE / UNRELIABLE, delta, top contributing features, avoid-list hits. With source_text/source_file_path, also accounts for every number and URL from the source — dropped numbers and dropped/broken URLs are reported. |
get_exemplars |
Verbatim exemplar paragraphs from included samples of one genre (the retrieval bank agents draft against). |
get_profile |
The readable profile + fingerprint summary (effective values, which are user-corrected), bands, avoid list. |
ingest_sample |
Add writing (exactly one of text / file_path / url). Title, genre, and authorship (sole/blended) are required — attribution is never silently defaulted. Never recomputes the fingerprint. |
list_corpus |
The corpus manifest: metadata, word counts, included flags, totals. |
recompute_fingerprint |
Recompute from included samples and re-derive the bands. dry_run: true previews the induced feature deltas and band shifts without saving — review before you apply. |
Protocol: MCP over stdio on rmcp 3.8 (the official Rust MCP SDK),
modern era only (protocol version 2026-07-28). Sessions open with
server/discover and every request carries its protocol version in
_meta — there is no initialize handshake. Legacy-era contact is
refused at the stdio front door with the typed -32022
unsupported-version error. Fail-closed throughout: malformed frames,
unknown tools, strict argument schemas, named size bounds everywhere.
Versions (1.0 release): the MCP server eigenstyle, the TUI, and
the GUI are 1.0.0. eigenstyle-core stays at 0.1.0 — that version
is already published on crates.io and does not move with this
release.
Adding your writing
- MCP: an agent calls
ingest_sample(or you ask for a URL fetch — the core fetches it, bounded, HTML reduced to text). - TUI:
Add writingscreen (key2) — title, genre, authorship toggle, source, then a file path (Enter loads it) or pasted text; Ctrl+S saves. - GUI:
Add writingtab — same fields as clickable boxes; the authorship button toggles sole/blended; Add sample saves.
In every flow the same rules hold: samples are append-only (exclude a sample from the fingerprint instead of deleting history), and the fingerprint never changes silently — recompute is explicit, with a dry-run preview first.
Correcting the fingerprint
The fingerprint dashboard (TUI Fingerprint screen, GUI Fingerprint
tab) lists every feature's mean/SD. Select one, type a corrected mean,
apply: the value is stored as a user correction overlaid on the
computed reference. Corrections survive recompute, are marked wherever
they show, and can be cleared wholesale to restore computed values
exactly.
Patterns adapted from same-kind tools
- HumanifyMe — the editable, human-readable fingerprint, and the
deterministic post-draft verify gate (dropped numbers / broken URLs
in
check_draft). - brandvoice-mcp — ingest → chunk → exemplar retrieval bank
(
get_exemplarsserves corpus paragraphs by genre). - book-writer-mcp / Eden — per-genre style profiles (the dashboard shows pooled per-genre stats), and the builder flow where induced rules are shown for correction before they are saved (recompute dry-run preview → apply).
- Arcitext — tone-fit via an explicit avoid list, enforced by the checker and editable in the Profile view.
Bounds (named, enforced)
Sample text ≤ 256 KiB and ≥ 10 tokens; draft ≤ 1 MiB, < 200 words = UNRELIABLE verdict (integrity/avoid checks still run); URL fetch ≤ 1 MiB, 15 s, HTTP(S) only, ≤ 3 redirects; JSON-RPC line ≤ 4 MiB; fingerprint build needs ≥ 2 included pieces (leave-one-out calibration is undefined below that) and fails closed otherwise.
Platform notes
- Toolchain pinned to Rust 1.99.0 (
rust-toolchain.toml), matching the estate. GPUI is pinned exactly:gpui-ce = =0.2.2+gpui_ce_platform = =0.1.0(features wayland, x11). - GUI rendering is verified on Wayland (primo's desktop is Hyprland; the smoke runs under a headless wlroots compositor). Under Xvfb/X11 this GPUI build presents black frames — use a Wayland session.
- GUI text entry is click-to-focus, append/backspace only (no selection/IME yet) — a stated limit, tracked in PROGRESS.md.
Layout
crates/eigenstyle-core corpus store, stylometry, fingerprint build, checker, fetch
crates/eigenstyle stdio MCP server (6 tools)
crates/eigenstyle-tui ratatui TUI (eigenstyle-tui --snapshot <screen> renders headlessly)
crates/eigenstyle-gui GPUI GUI
screenshots/ smoke evidence (GUI corpus + fingerprint views, probe)
License
This project is licensed under the Apache License, Version 2.0.
Eigenstyle MCP questions
What tools does Eigenstyle MCP provide?
It exposes 8 tools, including check_draft, get_exemplars, get_profile, ingest_sample, list_corpus.
Can I manually correct the writing fingerprint?
Yes, you can select a feature in the dashboard and apply a user-corrected mean which is overlaid on the computed reference.
What happens if a draft is too short?
If a draft is under 200 words, it receives an UNRELIABLE verdict.