Provider REST API

13 actions

Connect Claude to Asana

Search, file and update Asana tasks, and read the projects, sections and people around them. Toolspoke puts 13 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Personal access token
Actions exposed: 13
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Asana
Open the marketplace in your workspace, add Asana to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with personal access token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Asana shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Asana asks for

Personal access token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Personal access tokenRequired: Asana → your profile photo → My settings → Apps → Manage developer apps → Personal access tokens. The token acts as you, with exactly your own Asana permissions.; 2/1200000000000000/1200000000000000:abc…
Default workspace IDOptional: Used whenever an action is called without an explicit workspace_gid. Leave it blank to require one on every call; list_workspaces shows what this token can see.; 1200000000000000

What Claude can do in Asana

13 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 9Reads
Writes: 4Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

search_tasks
Search a workspace's tasks by free text and by any combination of assignee, project, section, tag, completion state and date window. This is the open-ended read - reach for it first, and use list_tasks only when you already know the exact project, tag or section to enumerate. Results are ordered by the sort you ask for and capped at 100; Asana's ordinary offset paging does not work here, so narrow the query rather than trying to page through it. Note that Asana restricts this endpoint to premium workspaces and answers a free one with a 402.
list_tasks
Enumerate the tasks of one project, section or tag, or one person's tasks in a workspace. IMPORTANT: Asana refuses a bare call - you must pass project, section or tag, OR pass assignee together with workspace_gid. Passing assignee without workspace_gid, or workspace_gid without assignee, is rejected with a 400 that reads like a malformed request rather than a missing filter. For anything more open-ended than that, use search_tasks.
get_task
Fetch one task in full: its description, dates, assignee, followers, tags, project memberships and custom field values. Use it after search_tasks or list_tasks when you need the actual content of a task rather than its summary. Comments are not part of a task record - they are stories, and there is no story listing in this connector.
list_projects
List the projects in a workspace, optionally narrowed to one team. Archived projects are excluded unless you ask for them. This is how you find the project gid that list_tasks, list_sections and create_task take.
get_project
Fetch one project in full, including its description, owner, team, dates, current status and custom field settings. Use list_projects to find the gid first.
list_sections
List the sections of one project, in board or list order. Sections are the columns of a board and the headings of a list, and their gids are what list_tasks takes as `section`.
list_workspaces
List the workspaces and organizations this token can see. Call it first when you do not know which workspace to act on, and to find out whether the connection reaches anything at all - an empty list means the token is valid but belongs to no workspace. The gid returned here is what every workspace_gid argument takes.
list_users
List the people in a workspace, or in one team, with their names and email addresses. Use it to find the user gid that create_task and update_task take as `assignee`, and that search_tasks filters on.
list_tags
List the tags defined in a workspace, with their gids and colours. Tags are how Asana marks work across projects, and these gids are what search_tasks and list_tasks filter on and what create_task applies.

Writes

Creates or updates something on the other side.

create_task
File a new task. Asana needs somewhere to put it: pass either project_gids or workspace_gid - a task with neither is rejected. assignee takes a user gid, an email address, or the literal "me". Returns the created task including its gid and permalink URL.
update_task
Change fields on an existing task: rename it, rewrite the description, move the due date, reassign it or reparent it. Pass only the fields you want changed; anything omitted is left alone. Use complete_task to tick a task off, and note that projects and tags cannot be changed here - Asana treats those as create-only on the task record.
complete_task
Mark a task complete, or reopen one by passing completed as false. This is the same PUT /tasks/{gid} endpoint update_task uses, separated out so completing a task is one unambiguous call rather than a field an agent has to remember to set. Completing a task in Asana is reversible and notifies its followers.
add_comment
Post a comment on a task. Asana calls comments stories, and this creates one of resource_subtype comment_added on the task's story collection. Send either text or html_text, not both - html_text takes Asana's restricted HTML and must be wrapped in a <body> element. Everyone following the task is notified.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 13 actions above are the whole of it. A call to any other name is refused before it reaches Asana rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
Nothing here deletes: This connector writes to Asana, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Asana of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Asana: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Asana. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Asana's own rate limits. A call that Asana refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Asana?

13 named actions: 9 that only read and 4 that write. They include search_tasks, list_tasks and get_task. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Asana connector need?

Personal access token. The connector asks for personal access token, and optionally default workspace id. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Asana connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 13 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Asana connector not do?

The 13 actions above are the whole of it. A call to any other name is refused before it reaches Asana rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Asana, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Asana of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Asana. An agent has to ask. Toolspoke does not retry, queue or back off around Asana's own rate limits. A call that Asana refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Asana's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Asana?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More project management connectors

Browse all of them