add_person_to_project

THE RISK

Medium Risk

Why add_person_to_project needs a policy

This tool creates or modifies access permissions for people on a project. While it does not delete data (which would make it Destructive) or execute arbitrary code (Execute), it irreversibly alters project membership and access control. However, the change is theoretically reversible through the removal of access.

From the tool's definition Tool description states 'Grant access to one or more people for a project' — a clear modification of project access permissions. The verb 'grant access' indicates creation or modification of access control records.

Documented attack patterns abuse exactly the kind of access add_person_to_project gives an agent:

POLICY

How to control add_person_to_project

PolicyLayer is an MCP gateway — it sits between your AI agents and Basecamp MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_person_to_project:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_person_to_project": {
      "limits": [
        {
          "counter": "add_person_to_project_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_person_to_project stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Basecamp MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Basecamp MCP Server tools

Destructive delete_webhook Delete a webhook Destructive remove_person_from_project Revoke access from one or more people for a project Write reposition_todo Change the position/order of a todo within its list Write add_comment_to_card Add a comment to a card Write add_comment_to_document Add a comment to a document Write add_comment_to_message Add a comment/reply to a message Write add_comment_to_recording Add a comment to any Basecamp recording (universal comment tool) Write add_comment_to_todo Add a comment to a specific todo

All 56 Basecamp MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about add_person_to_project

What does the add_person_to_project tool do? +

Grant access to one or more people for a project. It is categorised as a Write tool in the Basecamp MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_person_to_project? +

Register the Basecamp MCP Server MCP server in PolicyLayer and add a rule for add_person_to_project: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Basecamp MCP Server. Nothing to install.

What risk level is add_person_to_project? +

add_person_to_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_person_to_project? +

Yes. Add a rate_limit block to the add_person_to_project rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block add_person_to_project completely? +

Set action: deny in the PolicyLayer policy for add_person_to_project. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides add_person_to_project? +

add_person_to_project is provided by the Basecamp MCP Server MCP server (qusaiisaleem/basecamp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Basecamp MCP Server tool call.

Start from Basecamp MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →