MCP Tool Reference High Risk

run

Execute a deployed Convex function with provided arguments

Part of the Convex MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

WHEN AI AGENTS USE THIS TOOL

AI agents invoke run to trigger processes or run actions in Convex. Execute operations can have side effects beyond the immediate call — triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

WHY ENFORCE A POLICY ON RUN

run can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.

RECOMMENDED POLICY

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

convex.yaml

tools:
  run:
    rules:
      - action: allow
        rate_limit:
          max: 10
          window: 60
        validate:
          required_args: true

See the full Convex policy for all 12 tools.

DETAILS

Tool Name

run

MORE CONVEX TOOLS

status Read

Query available deployments

tables Read

List all tables with declared/inferred schemas

data Read

Paginate through documents in a table

runOneoffQuery Read

Execute sandboxed read-only JS queries

functionSpec Read

Get metadata for all deployed functions

logs Read

Retrieve recent function execution log entries

insights Read

Fetch health insights for the deployment

envList Read

List all environment variables for a deployment

View all 12 tools →

SIMILAR EXECUTE TOOLS ON OTHER SERVERS

call-actor Apify

Call an Actor and get its run results

boot_simulator Appium

Boot an iOS simulator

setup_wda Appium

Download and setup WebDriverAgent for iOS simulators

install_wda Appium

Install and launch WebDriverAgent on an iOS simulator

auth0_deploy_action Auth0

Deploy an Auth0 action

auth0_publish_form Auth0

Publish an Auth0 form

FREQUENTLY ASKED QUESTIONS

What does the run tool do?

Execute a deployed Convex function with provided arguments. It is categorised as a Execute tool in the Convex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run?

Add a rule in your Intercept YAML policy under the tools section for run. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Convex MCP server.

What risk level is run?

run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run?

Yes. Add a rate_limit block to the run rule in your Intercept 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 run completely?

Set action: deny in the Intercept policy for run. 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 run?

run is provided by the Convex MCP server (get-convex/convex-backend). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

ENFORCE POLICIES ON CONVEX

Open source. One binary. Zero dependencies.

VIEW ON GITHUB Full Convex policy →

run