Run a full research workflow via the Head of Research agent. The Head decomposes your brief into specialist sub-questions, dispatches the right combination of 6 specialists (desk, trend, market, quant, qual, social) in parallel via async dispatch, polls them to completion, judges output quality, ...
Part of the Heista server.
Free to start. No card required.
AI agents invoke dispatch_head_of_research to trigger processes or run actions in Heista. 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.
dispatch_head_of_research can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"dispatch_head_of_research": {
"limits": [
{
"counter": "dispatch_head_of_research_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Heista policy for all 69 tools.
These attack patterns abuse exactly the kind of access dispatch_head_of_research gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run a full research workflow via the Head of Research agent. The Head decomposes your brief into specialist sub-questions, dispatches the right combination of 6 specialists (desk, trend, market, quant, qual, social) in parallel via async dispatch, polls them to completion, judges output quality, and returns a structured synthesis. Use for: any source-grounded research request — fact-checking, vendor teardowns, trend assessment, quantitative effect-size analysis, qualitative theme extraction, cross-platform discourse mapping, or any combination. Wall time: 2-5 min typical. Returns: { synthesis, head_session_id, status, event_count, tool_uses, elapsed_ms }. NOT for: non-research requests (writing, coding, casual chat) — respond directly without calling this. Cost: $0.20-1.50 per call depending on brief complexity (specialist token spend + Anthropic session-runtime at $0.08/hr).. It is categorised as a Execute tool in the Heista MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Heista MCP server in PolicyLayer and add a rule for dispatch_head_of_research: 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 Heista. Nothing to install.
dispatch_head_of_research is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the dispatch_head_of_research 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.
Set action: deny in the PolicyLayer policy for dispatch_head_of_research. 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.
dispatch_head_of_research is provided by the Heista MCP server (https://www.heista.co/api/mcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 69 Heista tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.