MCP server for Atlassian Confluence Data Center - access and manage content
Idiolect AI 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.
What it does
Write, rewrite, and refine in your own style. Build and manage your Writing Profile.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http idiolect-ai-mcp https://idiolect.app/api/mcp
# 2 — ask your agent for something these tools do
# write, rewrite, refine_writing and 2 more
Idiolect AI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http idiolect-ai-mcp https://idiolect.app/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
5 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.
Drafts an email, message, post, reply, doc, or report in the user's style. Use for new writing for or on behalf of the user, using their current Writing Profile when available. It writes from their request, facts, notes, or an outline, without inventing missing facts. The tool produces the draft. There is no need to draft it first. Works without a Writing Profile. Put the user's directions in `ins
| Parameter | Type | Required | Notes |
|---|---|---|---|
| profile | string | no | The Writing Profile's id or name. To use the current Writing Profile, omit profile. |
| request | string | no | What to write: the content, audience, purpose, and facts the user gave. Do not invent facts. Keep writing directions in instructions. Describe the intended author and point of view. Required unless |
| format | string | no | The form of the finished writing, such as email, LinkedIn post, Slack message, essay, release notes. |
| instructions | string | no | The user's directions about tone, length, structure, or exclusions, in their words. If none were given, omit instructions. Put content in request. Put a named output form in format. |
| language | string | no | The language for the finished writing, such as French. When the user requests a language, set language. Otherwise, follow the request or source text language. |
| requestAuthor | string | no | Who wrote the request. user: the user. host: the assistant. other: a third party. If unsure, omit requestAuthor. |
| evidence | object | no | The user's own writing or answers for their Writing Profile. |
| contextHints | object | no | Task-relevant context you already have for this piece, such as its audience, purpose, constraints, or preferences the user stated in this conversation. Keep the user's request itself in instructions |
| situation | object | no | — |
| setup | object | no | — |
Rewrites text: 'make this sound like me', 'less AI', shorter, or clearer. Use for writing for or on behalf of the user, including drafts the host wrote for them. It rewrites in the user's style using their current Writing Profile when available. It covers an email, message, post, reply, or doc, from a grammar fix to a complete rewrite. Covers asks such as 'make this less AI-written' or 'make it le
| Parameter | Type | Required | Notes |
|---|---|---|---|
| profile | string | no | The Writing Profile's id or name. To use the current Writing Profile, omit profile. |
| text | string | no | The text to change. Required unless setup resumes a held request. |
| format | string | no | The form of the finished writing, such as email, LinkedIn post, Slack message, essay, release notes. |
| instructions | string | no | The user's change request, in their words. Keep it separate from the text to change. |
| language | string | no | The language for the finished writing, such as French. When the user requests a language, set language. Otherwise, follow the request or source text language. |
| sourceAuthor | string | no | Who wrote this text. user: the user. host: the assistant. other: a third party. If unsure, omit sourceAuthor. Set it whenever you know who wrote the text. |
| evidence | object | no | The user's own writing or answers for their Writing Profile. |
| contextHints | object | no | Task-relevant context you already have for this piece, such as its audience, purpose, constraints, or preferences the user stated in this conversation. Keep the user's request itself in instructions |
| situation | object | no | — |
| setup | object | no | — |
Changes writing Idiolect AI returned, such as 'make it shorter and warmer'. The user does not need to name Idiolect AI again. It covers follow-ups on writing from write, rewrite, or refine_writing. The refine_writing tool revises returned writing, applies a ready-made template, or records its use. Send the latest writingJobVersionId, or outputReference when no version was returned, but
| Parameter | Type | Required | Notes |
|---|---|---|---|
| writingJobVersionId | string | no | Latest writingJobVersionId from write, rewrite, or refine_writing for this writing. Use outputReference when no version ID was returned. |
| outputReference | string | no | Owned outputReference from a writing result. Use it when no version ID was returned. It can record an outcome; a change requires saved writing history. |
| change | string | no | What the user wants changed in this version, in their words. Omit it when sending outcome. |
| format | string | no | Send only when this change gives the writing a new form, such as an email that becomes a Slack message. The value is the new form. Omit it to keep the current form. |
| language | string | no | Send only when this change asks for another language. The value is that language. Omit it to keep the language of the writing. |
| situation | object | no | Send only the facts of the situation that this change replaces, such as a new reader or a new constraint. Facts that you omit keep their earlier values. |
| outcome | string | no | Result reported by the user or observed by the host. kept: used as delivered. edited: changed and used. rejected: unusable. superseded: the request moved on. For edited, send known `finalTex |
| finalText | string | no | The known final wording, verbatim. Set editAuthor to whoever edited it. |
| comment | string | no | The user's critique or reason, in their words where possible. |
| decisionSource | string | no | Outcome source: user_told when the user said it, or host_observed when the host observed it. Omit when unknown. |
| editAuthor | string | no | Editor of finalText: user, host for assistant edits, other for another writer, or unknown. Without finalText, omit editAuthor. |
| templateId | string | no | A ready-made template to apply to this writing. |
Shows the user's current Writing Profile and rules, and lists their Writing Profiles. To view another Writing Profile, set profile to its id or name. To list its writing samples, set samples true. Writing Profiles update continuously as the user writes, so read the current one here each time instead of keeping a saved copy.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| profile | string | no | The Writing Profile's id or name. To use the current Writing Profile, omit profile. |
| samples | boolean | no | To list the Writing Profile's writing samples instead of its summary, set samples true. |
| cursor | string | no | With samples: the nextCursor from the previous page. |
Change the user's Writing Profiles and default writing template. Choose an action: create_profile, add_samples, remove_sample, add_rule, remove_rule, rename_profile, set_current_profile, or set_default_template. When the user shares writing they authored in this conversation, save it with add_samples. Without a Writing Profile, use create_profile. When the user states a lasti
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| profile | string | no | The Writing Profile's id or name. For set_current_profile, this is required. For add_rule, omit it to apply the rule to all Writing Profiles. Otherwise, omit it for the current Writing Profile. |
| evidence | object | no | For create_profile or add_samples. The user's own text or answers, shared or approved for their Writing Profile. Exclude prompts, AI text, templates, signatures, quotations, and forwarded text. `a |
| name | string | no | For rename_profile (required) or create_profile. |
| writingJobVersionId | string | no | For create_profile: the held writing to finish once the Writing Profile is ready. |
| rule | string | no | For add_rule: a lasting preference the user stated, in their words. Preserve its stated scope. Do not send inferred patterns. |
| scope | object | no | For add_rule across Writing Profiles: the situation the user stated. If it applies everywhere, omit scope. Do not combine scope with profile. |
| ruleId | string | no | For remove_rule: the rule id from view_writing_profile. |
| sampleId | string | no | For remove_sample: the sample id from view_writing_profile. |
| templateId | string | no | Without a Writing Profile, use this for set_default_template. Send templateId or clear, but not both. |
| clear | boolean | no | For set_default_template: clear the default template. Send clear or templateId, but not both. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Idiolect AI or to call it, at any volume.
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.2.
No release note was published with this version.
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.
Any signed-in account that does not publish Idiolect AI can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.