Write a finished prospectus markdown to the MPA prospectus inbox and mark the pipeline row as generated. The markdown will be auto-rendered to PDF by the systemd path watcher. Returns the markdown path and the expected PDF path.
AI agents use crow_consulting_write_prospectus to create or update resources in Crow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crow environment.
This tool creates a new markdown document and updates pipeline state in a project management system. While it has side effects (file creation and state modification), these are reversible—the generated files and records can be deleted or modified. It does not execute arbitrary code, delete irreversibly, or involve financial transactions.
From the tool's definition Tool explicitly performs 'Write a finished prospectus markdown' and 'mark the pipeline row as generated', indicating creation and modification of data (markdown file and database row state).
Documented attack patterns abuse exactly the kind of access crow_consulting_write_prospectus gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_consulting_write_prospectus:
{
"version": "1",
"default": "deny",
"tools": {
"crow_consulting_write_prospectus": {
"limits": [
{
"counter": "crow_consulting_write_prospectus_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}crow_consulting_write_prospectus 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.
Free to start. No card required.
Write a finished prospectus markdown to the MPA prospectus inbox and mark the pipeline row as generated. The markdown will be auto-rendered to PDF by the systemd path watcher. Returns the markdown path and the expected PDF path. It is categorised as a Write tool in the Crow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crow MCP server in PolicyLayer and add a rule for crow_consulting_write_prospectus: 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 Crow. Nothing to install.
crow_consulting_write_prospectus 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 crow_consulting_write_prospectus 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 crow_consulting_write_prospectus. 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.
crow_consulting_write_prospectus is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.