
Eigenstyle
ai.qompassPublished by qompass.aiv0.1.1Updated Nov 2, 2026
MCP server for a personal voice profile: corpus, fingerprint, and draft-checking tools.
Overview
Local MCP server that keeps a measured writing-voice profile and lets an assistant check drafts against it, pull exemplars, and add samples.
- What you can do
- Score a draft (text or file) against the voice profile, with verdict, delta, top contributing features and avoid-list hits, optionally verifying numbers and URLs from a source text
- Retrieve verbatim exemplar paragraphs from included samples of a chosen genre
- Read the readable profile and fingerprint summary, including bands, avoid list and user corrections
- Add writing samples from text, a file path or a fetched URL, with required title, genre and authorship
- List the corpus manifest with metadata, word counts and totals
- Recompute the fingerprint and bands from included samples, with a dry-run preview before saving
- When to use it
- Useful when you want an assistant to draft or edit text in your own measured style and to check whether a draft has drifted from it, or when you want a corpus of your writing to serve as a retrieval bank for drafting.
- Requirements
- Runs as a local process over stdio; the README builds it from a Rust workspace with a pinned toolchain, and a packaged mcpb release is offered. Data lives in a store at EIGENSTYLE_HOME or a default local directory, seeded on first open. No authentication or API keys are declared. The desktop GUI needs a Wayland session.
Installation
In SourceWeft
- Open Eigenstyle in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
eigenstyle — 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.
[License: Apache 2.0]
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
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
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
License
This project is licensed under the Apache License, Version 2.0.
Source: README.md at commit db3351d
Tools
0Version history
1- v0.1.1LatestOct 19, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts