workflow_orchestrator
Meta-tool that CHAINS multiple MCP tools sequentially into a named workflow — delivering a composite output in a single call. 10 predefined workflows: compliance_full_audit (6 steps: KYC+sanctions+AI_gov+privacy+ESRS+CSRD), deal_due_diligence (7 steps: deep_dive+registry+court+patents+KYC+financi...
This record as markdown: /tools/io-github-getgapup-mcp-knowledge/workflow-orchestrator.md
What workflow_orchestrator does on Mcp Knowledge
AI agents invoke workflow_orchestrator to trigger actions in Mcp Knowledge. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
async | boolean | — | If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti |
params | object | — | Optional overrides passed to sub-tools. Keys depend on workflow (e.g., country, sector, role, drug, technology, wallet_address, acquirer). |
target | object | Yes | The entity to analyze. A company name for most workflows; location for climate_property_assessment; role+country for talent_market_brief. |
workflow | string | Yes | Named workflow to execute. Each workflow chains 3-7 tools sequentially. |
skip_failed_steps | boolean | — | Default true: continue on step failure. Set false to abort on first error. |
Parameters from the server's own tool schema.
Why workflow_orchestrator is rated High
This tool orchestrates and executes chains of other tools sequentially, triggering external operations across KYC, sanctions checks, registry lookups, patent searches, financial analysis, and more.
From the tool's definition Meta-tool that CHAINS multiple MCP tools sequentially into a named workflow — delivering a composite output in a single call
Attacks that exploit this kind of access
The rule that runs workflow_orchestrator safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Knowledge, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For workflow_orchestrator, this is the rule to start with:
workflow_orchestrator stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Knowledge, apply this rule, and every workflow_orchestrator call is checked against it from then on.
Questions about workflow_orchestrator
Meta-tool that CHAINS multiple MCP tools sequentially into a named workflow — delivering a composite output in a single call. 10 predefined workflows: compliance_full_audit (6 steps: KYC+sanctions+AI_gov+privacy+ESRS+CSRD), deal_due_diligence (7 steps: deep_dive+registry+court+patents+KYC+financials+M&A), market_entry_brief (6 steps: country_study+regulations+procurement+tax+AGOA+market_brief), competitor_intelligence_pack (5 steps: deep_dive+intel+patents+earnings+pitch_deck), esg_360 (5 steps: ESG_audit+carbon+CSRD+ESRS+supplier_esg), ip_freedom_to_operate (4 steps: patent_search+async_deep+IP_audit+competitive), climate_property_assessment (3 steps: climate_risk+real_estate+geo), pharma_target_screen (4 steps: trials+adverse_events+patents+meta_analysis), sanctions_360 (5 steps: KYC+Russian_sec+registry+crypto_wallet+court_filings), talent_market_brief (4 steps: salary+trends+adjacent_roles+skills_taxonomy). Returns steps_executed, consolidated P0/P1/P2 signals, overall_status, estimated_cost_usd, and raw outputs per step. Cache: 1h LRU per (workflow, target). Budget: 60s global timeout → partial if exceeded. Use when an agent needs a composite liverable without orchestrating tools manually. It is categorised as a Execute tool in the Mcp Knowledge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
workflow_orchestrator accepts 5 parameters: async, params, target, workflow, skip_failed_steps. Required: target, workflow. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Knowledge MCP server in PolicyLayer and add a rule for workflow_orchestrator: 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 Mcp Knowledge. Nothing to install.
workflow_orchestrator 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 workflow_orchestrator 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 workflow_orchestrator. 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.
workflow_orchestrator is provided by the Mcp Knowledge MCP server (https://mcp.gapup.io). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Knowledge, and thousands of servers like it.
Across the catalogue