paperdock
Registry code: 31a80b38a099bbc2
PaperDock exposes projects according to the connected account's current PaperDock memberships and roles. Start with list_projects; a successful response confirms the connection. Use the exact projectId in every project tool call, ask the user when the target is ambiguous, and keep projectId out of user-facing responses unless explicitly requested. Use list_files to inspect paths, search_files when the requested word, phrase, citation key, label, command, or other text may appear in unknown files, and read_file directly when the target file is already known. For a localized task in a large…
- endpoint
- https://app.paperdock.dev/api/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is paperdock live?
- Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
- Is paperdock free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does paperdock have?
- 14 tools: list_chat_messages, list_files, create_project, search_files, edit_file, create_comment, reply_to_comment, send_chat_message, ….
- Is paperdock safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.8%· all time 99.8%
last good check
of 14 tools
- degraded → live
- live → degraded· HTTP 503
- degraded → live
- unknown → live
- used for
- read and edit latex project files
- search text across project files
- comment on a latex document
- get compiled pdf of a project
- takes → gives
- text, code → text, documents
- tools
- 7 reads6 changes data1 sends messages
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
list_chat_messages reads auth-required 17h ago
Read recent project chat messages in chronological order.
{ "type": "object", "required": [ "projectId" ], "properties": { "limit": { "type": "integer", "maximum": 200, "minimum": 1 }, "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 18 lineslist_files reads auth-required never probed
List project file metadata without loading full file contents.
{ "type": "object", "required": [ "projectId" ], "properties": { "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 13 linescreate_project changes data auth-required never probed
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.
{ "type": "object", "required": [ "name" ], "properties": { "name": { "type": "string", "maxLength": 120, "minLength": 1 } }, "additionalProperties": false }arguments 14 linessearch_files reads auth-required never probed
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.
{ "type": "object", "required": [ "projectId", "query" ], "properties": { "limit": { "type": "number", "maximum": 50, "minimum": 1 }, "query": { "type": "string", "minLength": 1 }, "projectId": { "type": "string", "format": "uuid" }, "extensions": { "type": "array", "items": { "type": "string" } } }, "additionalProperties": false }arguments 29 linesedit_file changes data auth-required never probed
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.
{ "type": "object", "allOf": [ { "oneOf": [ { "required": [ "fileId" ] }, { "required": [ "path" ] } ] }, { "oneOf": [ { "required": [ "operations" ] }, { "required": [ "content" ] }, { "required": [ "rangeToken", "insert" ] } ] } ], "required": [ "projectId", "baseRevision" ], "properties": { "path": { "type": "string", "minLength": 1 }, "fileId": { "type": "string", "format": "uuid" }, "insert": { "type": "string" }, "content": { "type": "string" }, "projectId": { "type": "string", "format": "uuid" }, "operations": { "type": "array", "items": { "type": "object", "required": [ "expectedText", "from", "insert", "to" ], "properties": { "to": { "type": "integer", "minimum": 0 }, "from": { "type": "integer", "minimum": 0 }, "insert": { "type": "string" }, "expectedText": { "type": "string" } }, "additionalProperties": false }, "maxItems": 5000, "minItems": 1 }, "rangeToken": { "type": "string", "maxLength": 2048, "minLength": 1 }, "baseRevision": { "type": "integer", "minimum": 0 }, "expectedUpdatedAt": { "type": "string" } }, "additionalProperties": false }arguments 107 linescreate_comment changes data auth-required never probed
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.
{ "type": "object", "oneOf": [ { "required": [ "fileId" ] }, { "required": [ "path" ] } ], "required": [ "projectId", "body" ], "properties": { "body": { "type": "string", "maxLength": 4000 }, "path": { "type": "string", "minLength": 1 }, "quote": { "type": "string", "maxLength": 1000 }, "fileId": { "type": "string", "format": "uuid" }, "projectId": { "type": "string", "format": "uuid" }, "selectionTo": { "type": "integer", "minimum": 0 }, "contextAfter": { "type": "string", "maxLength": 500 }, "contextBefore": { "type": "string", "maxLength": 500 }, "selectionFrom": { "type": "integer", "minimum": 0 } }, "additionalProperties": false }arguments 58 linesreply_to_comment changes data auth-required never probed
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.
{ "type": "object", "required": [ "projectId", "commentId", "body" ], "properties": { "body": { "type": "string" }, "commentId": { "type": "string", "format": "uuid" }, "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 22 linessend_chat_message sends messages auth-required never probed
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.
{ "type": "object", "required": [ "projectId", "body" ], "properties": { "body": { "type": "string", "maxLength": 4000 }, "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 18 linesread_pdf reads auth-required 17h ago
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.
{ "type": "object", "required": [ "projectId", "path" ], "properties": { "path": { "type": "string", "minLength": 1, "description": "Project-relative entry .tex path, such as main.tex. Not a PDF path or URL." }, "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 19 linesupload_file changes data auth-required never probed
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.
{ "type": "object", "oneOf": [ { "required": [ "content" ] }, { "required": [ "contentBase64" ] } ], "required": [ "projectId", "path" ], "properties": { "path": { "type": "string", "minLength": 1 }, "sha256": { "type": "string" }, "content": { "type": "string" }, "mimeType": { "type": "string" }, "projectId": { "type": "string", "format": "uuid" }, "contentBase64": { "type": "string" } }, "additionalProperties": false }arguments 42 linescreate_file changes data auth-required never probed
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.
{ "type": "object", "required": [ "projectId", "path", "content" ], "properties": { "path": { "type": "string", "minLength": 1 }, "content": { "type": "string" }, "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 22 linesread_file reads auth-required never probed
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.
{ "type": "object", "oneOf": [ { "required": [ "fileId" ] }, { "required": [ "path" ] } ], "required": [ "projectId" ], "properties": { "path": { "type": "string", "minLength": 1 }, "fileId": { "type": "string", "format": "uuid" }, "lineRange": { "type": "object", "required": [ "startLine", "endLine" ], "properties": { "endLine": { "type": "integer", "minimum": 1 }, "startLine": { "type": "integer", "minimum": 1 } }, "additionalProperties": false }, "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 51 lineslist_projects reads auth-required 17h ago
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.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 lineslist_comments reads auth-required 9h ago
List active project comments and their replies. Resolved comment history is not returned by this tool.
{ "type": "object", "required": [ "projectId" ], "properties": { "projectId": { "type": "string", "format": "uuid" } }, "additionalProperties": false }arguments 13 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id31a80b38a099bbc2.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/31a80b38a099bbc2/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/31a80b38a099bbc2?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.