Create a multi-agent sequential execution chain. Defines a pipeline where multiple agents process data in sequence. Each stage is validated against the Blueprint before the next stage can proceed. Repair suggestions propagate forward through the chain. Different from submit_chain_stage: create_ch...
Risk signalsHandles credentials or secrets (api_key)
Part of the Governance Platform server.
Free to start. No card required.
AI agents use create_chain to create or modify resources in Governance Platform. 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 create_chain repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Governance Platform.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"create_chain": {
"limits": [
{
"counter": "create_chain_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Governance Platform policy for all 31 tools.
These attack patterns abuse exactly the kind of access create_chain gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Create a multi-agent sequential execution chain. Defines a pipeline where multiple agents process data in sequence. Each stage is validated against the Blueprint before the next stage can proceed. Repair suggestions propagate forward through the chain. Different from submit_chain_stage: create_chain defines the pipeline (stages, agent names, TTL); submit_chain_stage executes one stage of an already-created chain. Different from handoff_audit: handoff_audit verifies a transition between stages after they have been submitted. The Blueprint must already exist (use create_blueprint or load_rule_pack first). Each stage in the chain validates against the same Blueprint. Sibling tools: create_chain (define the pipeline), submit_chain_stage (advance through it), handoff_audit (verify between stages). Args: api_key: GeodesicAI API key (starts with gai_) blueprint: workflow_name of the Blueprint governing all stages stages: List of stage definitions, e.g. [{"stage_name": "extract", "agent_name": "PDF Scanner"}, {"stage_name": "validate", "agent_name": "QA Agent"}] Minimum 2 stages required. ttl: Chain timeout in seconds. After this many seconds without progress, the chain expires and submitted stages cannot be advanced. Default: 3600 (1 hour). Returns: chain_id: unique identifier for the chain (use this with submit_chain_stage and handoff_audit) status: initial chain status (typically "active") stages: list of stage records with stage_name, agent_name, and per-stage status next_stage: name of the first stage to submit ttl_seconds: echoed back for caller reference. It is categorised as a Write tool in the Governance Platform MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Governance Platform MCP server in PolicyLayer and add a rule for create_chain: 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 Governance Platform. Nothing to install.
create_chain 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 create_chain 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 create_chain. 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.
create_chain is provided by the Governance Platform MCP server (https://app.geodesiclabs.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 31 Governance Platform 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.