The server itself exposes 27 tools, and some of them can write to your Asana account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Asana.

How is this different from connecting Asana MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Asana MCP API changes?

We track the Asana MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Asana tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Asana?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Asana MCP server myself?

No. TrustGate connects to the Asana MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Asana directly.

Connect Asana MCP to your AI agents, securely.

One secured endpoint for every Asana call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Asana MCP now

What your agents can ask once Asana MCP is connected.

Select the tools your AI agents can call

27 tools from the Asana MCP schema.

Showing 27 tools

search_objectsreadUniversal search across Asana resource types: tasks, projects, portfolios, goals, teams, users, tags, custom fields and AI Teammates.
get_taskreadReturns full details for a single task: name, description, assignee, due dates, custom fields, project memberships, dependencies, subtasks and comments.
get_tasksreadReturns a filtered list of tasks by project, section, tag, user task list or assignee.
get_my_tasksreadReturns the tasks assigned to the currently authenticated user.
search_tasksreadAdvanced task search with full-text and complex filters across names, descriptions and comments. Premium accounts only.
create_taskswriteCreates one or more tasks immediately, up to 50 per call, with project, section, parent, assignee, dates and custom fields.
update_taskswriteUpdates one or more tasks in a single operation, up to 50 per call.
delete_taskhigh riskPermanently deletes a task and any subtasks not also in another project. This action cannot be undone.
get_projectreadReturns full details for a single project: name, description, owner, members, task counts and sections.
get_projectsreadReturns a list of projects in the workspace, optionally filtered by team or including archived projects.
get_status_overviewreadReturns an aggregated status report for one or more projects or portfolios, with status updates, task summaries and flagged blockers.
create_projectwriteCreates a new project, optionally with sections and tasks in a single operation.
get_portfolioreadReturns full details for a single portfolio, including name, owner and associated projects.
get_portfoliosreadReturns the portfolios owned by the authenticated user in the current workspace.
get_items_for_portfolioreadReturns the items inside a portfolio, including projects and goals.
get_mereadReturns the name, email and workspace memberships of the currently authenticated user.
get_userreadReturns details for a user by GID, email address or the string me.
get_usersreadReturns a list of users in the workspace, optionally filtered by team membership.
get_teamsreadReturns a list of teams in the workspace.
get_agentreadReturns the full record for a single AI Teammate agent by GID.
get_workspace_agentsreadReturns the AI Teammate agents configured in the workspace.
get_attachmentsreadReturns attachments for a task, project or project brief, with file names and download URLs.
add_commentwriteAdds a comment to a task, in plain text or HTML, with support for mentions and pinned comments.
create_project_status_updatewritePosts a status update to a project or portfolio with a title, status colour and body text.
create_task_previewwriteDrafts a task and presents it for review before creating it in Asana.
create_project_previewwriteDrafts a structured project plan and presents it for review before creating it in Asana.
search_tasks_previewreadSearches for tasks and displays the results in an interactive UI.

What Asana MCP exposes

Asana MCP groups its 27 tools into 6 categories, each with a suggested starting policy.

All 27 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Tasks	Task details, filtered lists, my tasks, advanced search, creation, updates and deletion	Read / Write	Require approval for deletes; batch writes affect up to 50 tasks
Projects	Project details, listings, creation and status overviews	Read / Write	Audit project creation
Portfolios	Portfolio details, listings and the items inside them	Read	Limit to intended portfolios
People & Teams	Authenticated user, users, teams and AI Teammate agents	Read	Limit organization access
Collaboration	Comments, status updates and attachments	Read / Write	Review content before posting
Interactive	Preview tools that render a confirmation UI before committing a change	Read / Write	Prefer preview tools over direct writes

Connect Asana MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Asana
Find Asana in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Asana MCP or block it. You allow the exact tools each agent can call, one by one.

Asana MCP	27 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 27 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Asana MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Asana MCP27 documented tools.
Coding assistants	Connection & credentialsper user	Tasks8 tools
Internal copilots	Tool access policiesdeny by default	People & Teams6 tools
Workflow automations	Request & response inspectioninline	Projects4 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools9 tools