MCP server for Tank - scan and publish AI agent skills from your editor
Nothing to run from here
Etincel Nonfiction is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
—
uptime 90d
0
calls last 7d
What it does
Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.
Quickstart
# 1 — run it from where its publisher ships it
npx -y etincel
# 2 — ask your agent something
> Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.
Etincel Nonfiction is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
ETAll 1 server
etincel1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way, and that is the choice that matters: behind our gateway it runs on the publisher’s own infrastructure and nothing of it touches your machine, while locally it starts as a process under your own user, with your files and your network.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add etincel-nonfiction-mcp -- npx -y etincelReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List every available style: premade emotional-tone presets, any voices the user has trained from their own samples, and (if a .etincelrc in the current repo defines one) the shared team style, id
No parameter schema on file.
Fetch the full drafting guide for one style (a preset id like
No parameter schema on file.
Analyze one or more of the user
No parameter schema on file.
Build a style profile from explicit dial values instead of writing samples: for when the user wants to hand-tune a voice (or doesn
No parameter schema on file.
No parameter schema on file.
Copy a style into a new trained voice under the given name, seeded with its persona dials and drafting guide. Two kinds of source: a premade preset (e.g.
No parameter schema on file.
Permanently delete a trained voice profile by id. Does not affect premade presets.
No parameter schema on file.
Set which style (preset or trained voice) should be used by default for this user going forward, so it doesn
No parameter schema on file.
Compare a piece of drafted text
No parameter schema on file.
Compare a piece of drafted text against a trained voice
No parameter schema on file.
Deterministically scan a piece of non-fiction text for common AI-writing tells: banned hype vocabulary, chatbot fingerprints, and structural patterns (uniform paragraph length, stacked transitions, em-dash overuse, rule-of-three compulsion, and more), plus this installer
No parameter schema on file.
No parameter schema on file.
Add a term to this installer
No parameter schema on file.
Remove a term from this installer
No parameter schema on file.
Add a term to this installer
No parameter schema on file.
Remove a term from this installer
No parameter schema on file.
Show the banned-words and custom (allowed) words lists for a scope: the global list (default), or a specific style
No parameter schema on file.
Save free-text drafting rules layered on top of a style
No parameter schema on file.
Remove the saved instructions for a scope (global, or a specific style), leaving it empty.
No parameter schema on file.
Show the saved instructions for a scope: the global instructions (default), or a specific style
No parameter schema on file.
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Etincel Nonfiction costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 95 / 100
Release 0.10.1 · scanned 7 Sep 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score99
Client score95
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest4205f0b775aba40a623f0d499ac6ba82e71c82390c2f61f5d0e641f367205ab6
Score vectorthreat 99 → client 95
| Term | Level | What it prices | Points |
|---|---|---|---|
| −1.2 | |||
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (20 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_styles | no tags | |
| get_style_guide | untrusted-input | |
| train_style | no tags | |
| create_style_from_dials | no tags | |
| update_style | no tags | |
| fork_style | untrusted-input | |
| delete_style | no tags | |
| set_default_style | no tags | |
| check_voice_match | no tags | |
| check_self_repetition | no tags | |
| audit_text | no tags | |
| second_read | no tags | |
| add_banned_word | no tags | |
| remove_banned_word | no tags | |
| add_custom_word | no tags | |
| remove_custom_word | no tags | |
| list_dictionary | no tags | |
| set_style_instructions | no tags | |
| clear_style_instructions | no tags | |
| get_style_instructions | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest4205f0b775aba40a
Scanned2026-09-07
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 0.10.1 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.10.1
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Etincel Nonfiction in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.