Business · MCP Server
Asana MCP: setup, permissions and security risks
The Asana MCP server gives an agent tasks, projects, portfolios, goals, and comments. That is useful, and it is also a set of real capabilities pointed at a real system. Here is what it exposes, why it is worth governing, and the policy to put in front of it.
Exposure grade C
4 of 7 points, default setup. Last checked .
| Returns text written by people outside your team | Yes, +2 |
| Can change things outside your machine | Yes, +1 |
| Can do something hard to undo | No |
| Can read local files or run code locally | No |
| Default credential is long-lived and broad | Yes, +1 |
| Advisory or disclosure in the 12 months before the check | No |
0–1 points is A, 2–3 B, 4 C, 5–6 D, 7 F. The grade measures how much the default setup can reach, not the quality of the code. The hardening options below lower it.
Setup
Through Prismor (console, OAuth)
# Console → MCP Hub → Recommended servers → Asana → Add
# Sign in to Asana and approve. Prismor stores the token for your org.
# Then serve it to agents from a hosted endpoint:
claude mcp add --transport http prismor https://<your-endpoint>/mcp \
--header "Authorization: Bearer <key>"Direct remote server hosted by Asana
https://mcp.asana.com/v2/mcp # OAuth with a registered Asana app; no dynamic client registrationHow it logs in
OAuth 2.0 with PKCE against an app registered in the Asana developer console. The server does not support dynamic client registration, so Prismor signs users in with its own registered Asana app. The token acts as the signed-in user.
Tools that change things
create and update taskscreate and update projectsadd commentsBuilt-in hardening
- Start in observe mode and review which Asana tools your agents call before you enforce.
- Block task creation and updates in a session that has just read untrusted task text.
- Switch off Asana tools an agent does not need on the server card in MCP Hub.
Known advisories and incidents
None published as of the check date.
What the server hands your agent
Search and read tasks, projects, portfolios, goals and users; create and update tasks and projects; add comments. In Prismor you add it from the console (MCP Hub, Recommended servers, Asana) and sign in to Asana. Your agents reach it through the Prismor gateway with the access your Asana account already has.
Why it is worth governing
- Task descriptions and comments are free text written by teammates, guests and form submissions, so they can carry instructions aimed at an agent.
- Created tasks, reassignments and due-date changes notify real people and drive their work.
- One sign-in covers every workspace and project the user can see, which is more than most agent tasks need.
Tag what the tools actually do
Prismor tags every tool by behavior rather than by name, so rules survive a server adding tools you have never seen. A sensible starting map for Asana:
| Tool pattern | Tags | Why |
|---|---|---|
| mcp__asana__*get* | untrusted_content | task bodies and comments are free text from many people |
| mcp__asana__*search* | untrusted_content | search results return the same free text |
| mcp__asana__*create* | critical_action | new tasks and comments notify the team |
| mcp__asana__*update* | critical_action | assignee and status changes start other people’s work |
Patterns are illustrative globs. Run prismor tags list to see how your installed tools actually resolve.
The policy
Rules read as a sentence: a tag, then or with another tag, and what to do about it. Note the mode - start by watching, not blocking.
settings:
tool_tags:
enabled: true
mode: observe # switch to enforce once the log looks right
tags:
"mcp__asana__*get*": [untrusted_content]
"mcp__asana__*search*": [untrusted_content]
"mcp__asana__*create*": [critical_action]
"mcp__asana__*update*": [critical_action]
rules:
- "untrusted_content then critical_action -> block"Putting Asana behind the gateway
You do not change the Asana server or how it is configured. Move your existing mcpServers block behind the Prismor gateway and point your agent at Prismor instead:
prismor mcp-gateway install # moves your .mcp.json servers behind the gateway
prismor mcp-gateway uninstall # restores the original, backup keptYour agent sees the same Asana tools, namespaced as mcp__asana__<tool>. Every call is evaluated against policy before it is forwarded, and every result is scanned as untrusted content before the model sees it.
Frequently asked questions
Is the Asana MCP server safe to give an AI agent?
It is as safe as the credential behind it and the policy in front of it. The server itself is not the problem: the risk is that an agent can combine Asana access with everything else in the session, with no record of what it did. Front it with a gateway that evaluates each call and logs the verdict.
Does Prismor replace the Asana MCP server?
No. You keep running the same server, unchanged. Prismor aggregates it behind a single connector so your agent sees the same tools, namespaced as mcp__<server>__<tool>, with every call and every result passing through policy first.
Will this block work my team actually needs to do?
Not if you start in observe mode. Every call is recorded with the decision that would have applied, and nothing is blocked. You promote rules to enforce once the log shows the policy matches how your agents really work.
What about tool results, not just tool calls?
Results are scanned as untrusted content before the model sees them. A response carrying injected instructions or poisoned output is withheld and replaced with the reason, which matters most for servers that return text other people wrote.
One gateway for every MCP server
Asana is one connector. The same policy covers the rest of them, plus the shell commands and file access your agents already have.
Other business servers
Asana is a trademark of its respective owner. Prismor is not affiliated with or endorsed by it. The Asana MCP server is third-party software; Prismor governs it the same way it governs any MCP server, without modifying it.