PaperDock
Overleaf alternative online LaTeX editor. AI agents edit, comment, and chat. Keep or revert edits.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"paperdock": {
"url": "https://app.paperdock.dev/api/mcp"
}
}
}Remote endpoints
https://app.paperdock.dev/api/mcpstreamable-httpWhat it can do
Tool inventory
Tools (14)
🟢list_projects
List standard PaperDock projects accessible to the connected account, including its current role and effective MCP capabilities for each. Use projectId only for subsequent tool calls and do not show it unless explicitly requested.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"projects": {
"items": {
"additionalProperties": false,
"properties": {
"capabilities": {
"additionalProperties": false,
"properties": {
"chatRead": {
"type": "boolean"
},
"chatWrite": {
"type": "boolean"
},
"commentRead": {
"type": "boolean"
},
"commentWrite": {
"type": "boolean"
},
"projectWrite": {
"type": "boolean"
},
"read": {
"type": "boolean"
},
"write": {
"type": "boolean"
}
},
"required": [
"chatRead",
"chatWrite",
"commentRead",
"commentWrite",
"projectWrite",
"read",
"write"
],
"type": "object"
},
"name": {
"type": "string"
},
"projectId": {
"type": "string"
},
"role": {
"enum": [
"owner",
"editor",
"viewer"
],
"type": "string"
}
},
"required": [
"capabilities",
"name",
"projectId",
"role"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"projects"
],
"additionalProperties": false
}🟡create_project(name)
Create a new PaperDock project with a starter main.tex only when the user explicitly asks. Names are unique per owner, ignoring letter case and leading/trailing spaces. On PROJECT_NAME_ALREADY_EXISTS, do not retry create_project with the same name or a case/whitespace-only variant. Call list_projects to find the existing project. If the user's intent is unclear, ask whether to use that project or create a new one with a different name. Never modify the existing project or choose a different name without the user's authorization.
Input Schema
{
"type": "object",
"properties": {
"name": {
"maxLength": 120,
"minLength": 1,
"type": "string"
}
},
"required": [
"name"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"initialFilePath": {
"const": "main.tex",
"type": "string"
},
"project": {
"additionalProperties": false,
"properties": {
"capabilities": {
"additionalProperties": false,
"properties": {
"chatRead": {
"type": "boolean"
},
"chatWrite": {
"type": "boolean"
},
"commentRead": {
"type": "boolean"
},
"commentWrite": {
"type": "boolean"
},
"projectWrite": {
"type": "boolean"
},
"read": {
"type": "boolean"
},
"write": {
"type": "boolean"
}
},
"required": [
"chatRead",
"chatWrite",
"commentRead",
"commentWrite",
"projectWrite",
"read",
"write"
],
"type": "object"
},
"name": {
"type": "string"
},
"projectId": {
"type": "string"
},
"role": {
"enum": [
"owner",
"editor",
"viewer"
],
"type": "string"
}
},
"required": [
"capabilities",
"name",
"projectId",
"role"
],
"type": "object"
}
},
"required": [
"initialFilePath",
"project"
],
"additionalProperties": false
}🟢list_files(projectId)
List project file metadata without loading full file contents.
Input Schema
{
"type": "object",
"properties": {
"projectId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"files": {
"items": {
"additionalProperties": false,
"properties": {
"kind": {
"enum": [
"source",
"asset"
],
"type": "string"
},
"mimeType": {
"type": [
"string",
"null"
]
},
"path": {
"type": "string"
},
"revision": {
"type": "integer"
},
"sizeBytes": {
"type": [
"integer",
"null"
]
}
},
"required": [
"kind",
"mimeType",
"path",
"revision",
"sizeBytes"
],
"type": "object"
},
"type": "array"
}
},
"required": [
"files"
],
"additionalProperties": false
}🟢search_files(extensions, limit, projectId, query)
Find where a word, phrase, citation key, label, LaTeX command, or other text appears across editable project files when its file or location is unknown. Search is case-insensitive and returns matching paths, positions, revisions, and short snippets. If the target file is already known, use read_file directly instead.
Input Schema
{
"type": "object",
"properties": {
"extensions": {
"items": {
"type": "string"
},
"type": "array"
},
"limit": {
"maximum": 50,
"minimum": 1,
"type": "number"
},
"projectId": {
"format": "uuid",
"type": "string"
},
"query": {
"minLength": 1,
"type": "string"
}
},
"required": [
"projectId",
"query"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"matches": {
"items": {
"additionalProperties": false,
"properties": {
"column": {
"type": "integer"
},
"line": {
"type": "integer"
},
"path": {
"type": "string"
},
"revision": {
"type": "integer"
},
"snippet": {
"type": "string"
},
"type": {
"const": "content",
"type": "string"
}
},
"required": [
"column",
"line",
"path",
"revision",
"snippet",
"type"
],
"type": "object"
},
"type": "array"
},
"searchedFiles": {
"type": "integer"
},
"truncated": {
"type": "boolean"
}
},
"required": [
"matches",
"searchedFiles",
"truncated"
],
"additionalProperties": false
}🟢read_file(fileId, lineRange, path, projectId)
Read an editable project file or return a 10-minute signed download URL for a private project asset. Provide exactly one target: fileId or path. For a localized task in a large text file, pass lineRange with inclusive 1-based startLine and endLine values to return at most 400 lines, absolute UTF-16 offsets, and a revision-bound rangeToken. If replacing all returned source lines, pass that rangeToken to edit_file instead of retyping the old text. Refine lineRange first when only part of the returned range should change. Omit lineRange when the full file is required.
Input Schema
{
"type": "object",
"properties": {
"fileId": {
"format": "uuid",
"type": "string"
},
"lineRange": {
"additionalProperties": false,
"properties": {
"endLine": {
"minimum": 1,
"type": "integer"
},
"startLine": {
"minimum": 1,
"type": "integer"
}
},
"required": [
"startLine",
"endLine"
],
"type": "object"
},
"path": {
"minLength": 1,
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId"
],
"additionalProperties": false,
"oneOf": [
{
"required": [
"fileId"
]
},
{
"required": [
"path"
]
}
]
}Output Schema
{
"type": "object",
"properties": {
"content": {
"type": "string"
},
"downloadUrl": {
"type": [
"string",
"null"
]
},
"file": {
"additionalProperties": false,
"properties": {
"kind": {
"enum": [
"source",
"asset"
],
"type": "string"
},
"mimeType": {
"type": [
"string",
"null"
]
},
"path": {
"type": "string"
},
"revision": {
"type": "integer"
},
"sizeBytes": {
"type": [
"integer",
"null"
]
}
},
"required": [
"kind",
"mimeType",
"path",
"revision",
"sizeBytes"
],
"type": "object"
},
"range": {
"additionalProperties": false,
"properties": {
"endLine": {
"type": "integer"
},
"endOffset": {
"type": "integer"
},
"rangeToken": {
"type": "string"
},
"startLine": {
"type": "integer"
},
"startOffset": {
"type": "integer"
},
"totalLines": {
"type": "integer"
},
"truncated": {
"type": "boolean"
}
},
"required": [
"endLine",
"endOffset",
"rangeToken",
"startLine",
"startOffset",
"totalLines",
"truncated"
],
"type": "object"
}
},
"required": [
"file"
],
"additionalProperties": false
}🟢read_pdf(path, projectId)
Get the latest successful compiled PDF for an explicit entry .tex path, with a signed download link valid for at most 10 minutes, size, generation time, and freshness information. This never compiles, waits, or polls. A newer running or failed compile may coexist with an older successful PDF. Freshness is unknown unless later source changes are detected; never assume the PDF matches current or unsaved source. Download and open the PDF using a PDF-capable tool before discussing its contents or layout; a link alone is not a PDF inspection. If no result exists or it has expired, ask the user to compile in the web app. Use read_file for uploaded PDF assets.
Input Schema
{
"type": "object",
"properties": {
"path": {
"description": "Project-relative entry .tex path, such as main.tex. Not a PDF path or URL.",
"minLength": 1,
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId",
"path"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"status": {
"enum": [
"available",
"not_compiled",
"unavailable"
],
"type": "string"
},
"mainPath": {
"type": "string"
},
"mimeType": {
"const": "application/pdf",
"type": "string"
},
"downloadUrl": {
"type": [
"string",
"null"
]
},
"downloadExpiry": {
"type": [
"string",
"null"
]
},
"compiledAt": {
"type": [
"string",
"null"
]
},
"sizeBytes": {
"type": [
"integer",
"null"
]
},
"freshness": {
"enum": [
"outdated",
"unknown"
],
"type": "string"
},
"latestCompileStatus": {
"enum": [
"queued",
"running",
"completed",
"failed",
"canceled",
"expired",
null
],
"type": [
"string",
"null"
]
},
"isLatestCompile": {
"type": "boolean"
},
"message": {
"type": "string"
}
},
"required": [
"status",
"mainPath",
"mimeType",
"downloadUrl",
"downloadExpiry",
"compiledAt",
"sizeBytes",
"freshness",
"latestCompileStatus",
"isLatestCompile",
"message"
],
"additionalProperties": false
}🟡upload_file(content, contentBase64, mimeType, path, projectId, ...)
Create one new editable text file from UTF-8 content. For compatibility contentBase64 is accepted only for UTF-8 text at an editable extension. Existing paths are never overwritten; use edit_file for existing text. Binary uploads and replacements are not supported by MCP: ask the user to upload or replace images, PDFs, and other binary assets directly in the PaperDock web app. Do not recreate them under another path or extension.
Input Schema
{
"type": "object",
"properties": {
"content": {
"type": "string"
},
"contentBase64": {
"type": "string"
},
"mimeType": {
"type": "string"
},
"path": {
"minLength": 1,
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
},
"sha256": {
"type": "string"
}
},
"required": [
"projectId",
"path"
],
"additionalProperties": false,
"oneOf": [
{
"required": [
"content"
]
},
{
"required": [
"contentBase64"
]
}
]
}Output Schema
{
"type": "object",
"properties": {
"file": {
"additionalProperties": false,
"properties": {
"kind": {
"enum": [
"source",
"asset"
],
"type": "string"
},
"mimeType": {
"type": [
"string",
"null"
]
},
"path": {
"type": "string"
},
"revision": {
"type": "integer"
},
"sizeBytes": {
"type": [
"integer",
"null"
]
}
},
"required": [
"kind",
"mimeType",
"path",
"revision",
"sizeBytes"
],
"type": "object"
},
"status": {
"const": "created",
"type": "string"
}
},
"required": [
"file",
"status"
],
"additionalProperties": false
}🟡create_file(content, path, projectId)
Create a new editable text file at a new project path from supplied content. Pass an explicit empty string to create an empty file. Existing paths are never overwritten.
Input Schema
{
"type": "object",
"properties": {
"content": {
"type": "string"
},
"path": {
"minLength": 1,
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId",
"path",
"content"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"file": {
"additionalProperties": false,
"properties": {
"kind": {
"enum": [
"source",
"asset"
],
"type": "string"
},
"mimeType": {
"type": [
"string",
"null"
]
},
"path": {
"type": "string"
},
"revision": {
"type": "integer"
},
"sizeBytes": {
"type": [
"integer",
"null"
]
}
},
"required": [
"kind",
"mimeType",
"path",
"revision",
"sizeBytes"
],
"type": "object"
},
"status": {
"const": "created",
"type": "string"
}
},
"required": [
"file",
"status"
],
"additionalProperties": false
}🔴edit_file(baseRevision, expectedUpdatedAt, fileId, operations, content, ...)
Immediately edit one existing editable text file and record the applied change in PaperDock's Review changes UI. Provide exactly one target (fileId or path) and exactly one payload: operations, content, or rangeToken with insert. Read the relevant current text first and pass its baseRevision. For a long replacement covering every line returned by an exact read_file.lineRange call, pass its rangeToken with insert; the token is connection-, file-, revision-, range-, and content-bound and expires after 10 minutes. For other focused edits, use sequential UTF-16 operations and copy expectedText exactly from read_file without retyping, normalization, spelling correction, or manual Unicode escaping; insertions use expectedText: "". On a conflict, read again and retry once. Use content only when broadly rewriting most of the file. This tool cannot create, rename, or delete files.
Input Schema
{
"type": "object",
"properties": {
"baseRevision": {
"minimum": 0,
"type": "integer"
},
"expectedUpdatedAt": {
"type": "string"
},
"fileId": {
"format": "uuid",
"type": "string"
},
"operations": {
"items": {
"additionalProperties": false,
"properties": {
"expectedText": {
"type": "string"
},
"from": {
"minimum": 0,
"type": "integer"
},
"insert": {
"type": "string"
},
"to": {
"minimum": 0,
"type": "integer"
}
},
"required": [
"expectedText",
"from",
"insert",
"to"
],
"type": "object"
},
"maxItems": 5000,
"minItems": 1,
"type": "array"
},
"content": {
"type": "string"
},
"insert": {
"type": "string"
},
"path": {
"minLength": 1,
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
},
"rangeToken": {
"maxLength": 2048,
"minLength": 1,
"type": "string"
}
},
"required": [
"projectId",
"baseRevision"
],
"additionalProperties": false,
"allOf": [
{
"oneOf": [
{
"required": [
"fileId"
]
},
{
"required": [
"path"
]
}
]
},
{
"oneOf": [
{
"required": [
"operations"
]
},
{
"required": [
"content"
]
},
{
"required": [
"rangeToken",
"insert"
]
}
]
}
]
}Output Schema
{
"type": "object",
"properties": {
"applicationStatus": {
"enum": [
"applied",
"applying",
"not_applied",
"pending_review"
],
"type": "string"
},
"file": {
"additionalProperties": false,
"properties": {
"kind": {
"enum": [
"source",
"asset"
],
"type": "string"
},
"mimeType": {
"type": [
"string",
"null"
]
},
"path": {
"type": "string"
},
"revision": {
"type": "integer"
},
"sizeBytes": {
"type": [
"integer",
"null"
]
}
},
"required": [
"kind",
"mimeType",
"path",
"revision",
"sizeBytes"
],
"type": "object"
}
},
"required": [
"applicationStatus",
"file"
],
"additionalProperties": false
}🟢list_comments(projectId)
List active project comments and their replies. Resolved comment history is not returned by this tool.
Input Schema
{
"type": "object",
"properties": {
"projectId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"comments": {
"items": {
"additionalProperties": false,
"properties": {
"authorType": {
"enum": [
"person",
"ai_agent"
],
"type": "string"
},
"body": {
"type": "string"
},
"filePath": {
"type": "string"
},
"quote": {
"type": "string"
},
"commentId": {
"type": "string"
},
"replies": {
"items": {
"additionalProperties": false,
"properties": {
"authorType": {
"enum": [
"person",
"ai_agent"
],
"type": "string"
},
"body": {
"type": "string"
}
},
"required": [
"authorType",
"body"
],
"type": "object"
},
"type": "array"
},
"selectionFrom": {
"type": "integer"
},
"selectionTo": {
"type": "integer"
},
"status": {
"enum": [
"open",
"resolved"
],
"type": "string"
}
},
"required": [
"authorType",
"body",
"filePath",
"quote",
"commentId",
"replies",
"selectionFrom",
"selectionTo",
"status"
],
"type": "object"
},
"type": "array"
},
"status": {
"const": "open",
"type": "string"
}
},
"required": [
"comments",
"status"
],
"additionalProperties": false
}🔴create_comment(body, contextAfter, contextBefore, fileId, path, ...)
Create an open Comment on a .tex project file and post it immediately to project collaborators without changing the source file. Later deletion cannot undo prior delivery or reading. Selection offsets may be inferred from quote. Provide exactly one target: fileId or path.
Input Schema
{
"type": "object",
"properties": {
"body": {
"maxLength": 4000,
"type": "string"
},
"contextAfter": {
"maxLength": 500,
"type": "string"
},
"contextBefore": {
"maxLength": 500,
"type": "string"
},
"fileId": {
"format": "uuid",
"type": "string"
},
"path": {
"minLength": 1,
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
},
"quote": {
"maxLength": 1000,
"type": "string"
},
"selectionFrom": {
"minimum": 0,
"type": "integer"
},
"selectionTo": {
"minimum": 0,
"type": "integer"
}
},
"required": [
"projectId",
"body"
],
"additionalProperties": false,
"oneOf": [
{
"required": [
"fileId"
]
},
{
"required": [
"path"
]
}
]
}Output Schema
{
"type": "object",
"properties": {
"comment": {
"additionalProperties": false,
"properties": {
"authorType": {
"enum": [
"person",
"ai_agent"
],
"type": "string"
},
"body": {
"type": "string"
},
"filePath": {
"type": "string"
},
"quote": {
"type": "string"
},
"commentId": {
"type": "string"
},
"replies": {
"items": {
"additionalProperties": false,
"properties": {
"authorType": {
"enum": [
"person",
"ai_agent"
],
"type": "string"
},
"body": {
"type": "string"
}
},
"required": [
"authorType",
"body"
],
"type": "object"
},
"type": "array"
},
"selectionFrom": {
"type": "integer"
},
"selectionTo": {
"type": "integer"
},
"status": {
"enum": [
"open",
"resolved"
],
"type": "string"
}
},
"required": [
"authorType",
"body",
"filePath",
"quote",
"commentId",
"replies",
"selectionFrom",
"selectionTo",
"status"
],
"type": "object"
}
},
"required": [
"comment"
],
"additionalProperties": false
}🔴reply_to_comment(body, projectId, commentId)
Post a reply under the connected PaperDock account, marked as created via an AI agent, immediately to an open Comment. Use a commentId returned by list_comments or copied from PaperDock. If a Comment is not found, call list_comments once and do not retry the same missing commentId. It is visible to project collaborators, and later removal cannot undo prior delivery or reading. Write body as natural, collaborator-facing prose.
Input Schema
{
"type": "object",
"properties": {
"body": {
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
},
"commentId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId",
"commentId",
"body"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"commentId": {
"type": "string"
},
"reply": {
"additionalProperties": false,
"properties": {
"authorType": {
"enum": [
"person",
"ai_agent"
],
"type": "string"
},
"body": {
"type": "string"
}
},
"required": [
"authorType",
"body"
],
"type": "object"
}
},
"required": [
"commentId",
"reply"
],
"additionalProperties": false
}🟢list_chat_messages(limit, projectId)
Read recent project chat messages in chronological order.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"maximum": 200,
"minimum": 1,
"type": "integer"
},
"projectId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"messages": {
"items": {
"additionalProperties": false,
"properties": {
"authorType": {
"enum": [
"person",
"ai_agent"
],
"type": "string"
},
"body": {
"type": "string"
}
},
"required": [
"authorType",
"body"
],
"type": "object"
},
"type": "array"
},
"truncated": {
"type": "boolean"
}
},
"required": [
"messages",
"truncated"
],
"additionalProperties": false
}🔴send_chat_message(body, projectId)
Post a message under the connected PaperDock account, marked as created via an AI agent, immediately to the selected private PaperDock project's Chat. It is visible to project members, and later editing or deletion cannot undo prior delivery or reading.
Input Schema
{
"type": "object",
"properties": {
"body": {
"maxLength": 4000,
"type": "string"
},
"projectId": {
"format": "uuid",
"type": "string"
}
},
"required": [
"projectId",
"body"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"message": {
"additionalProperties": false,
"properties": {
"authorType": {
"enum": [
"person",
"ai_agent"
],
"type": "string"
},
"body": {
"type": "string"
}
},
"required": [
"authorType",
"body"
],
"type": "object"
}
},
"required": [
"message"
],
"additionalProperties": false
}Community
Evidence