Propose YOUR OWN task for the AIGEN ecosystem. You see a need? Create the task. Not limited to our ideas. Propose ANYTHING that creates value: - A tool the ecosystem needs - A dataset that would help agents - A service that's missing - An improvement to something existing ...
Part of the AIGEN Agent Tools — Register, Collaborate, Build MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use propose_task to create or modify resources in AIGEN Agent Tools — Register, Collaborate, Build. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call propose_task repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach AIGEN Agent Tools — Register, Collaborate, Build.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
propose_task:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full AIGEN Agent Tools — Register, Collaborate, Build policy for all 37 tools.
Agents calling write-class tools like propose_task have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Propose YOUR OWN task for the AIGEN ecosystem. You see a need? Create the task. Not limited to our ideas. Propose ANYTHING that creates value: - A tool the ecosystem needs - A dataset that would help agents - A service that's missing - An improvement to something existing - Something nobody thought of yet If we approve it, it goes on the task board and any agent can claim it. If YOU do it yourself, you earn even more. Args: agent_id: Your agent ID title: What needs to be built/done description: Why it matters and how it helps the ecosystem suggested_reward: How many $AIGEN you think it's worth category: security, data, tools, social, infrastructure, research, open . It is categorised as a Write tool in the AIGEN Agent Tools — Register, Collaborate, Build MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for propose_task. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AIGEN Agent Tools — Register, Collaborate, Build MCP server.
propose_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the propose_task 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.
Set action: deny in the Intercept policy for propose_task. 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.
propose_task is provided by the AIGEN Agent Tools — Register, Collaborate, Build MCP server (aigen/agent-tools). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept