ld_architect
Architecte formation & développement — Gapup agent-payable C-suite expertise (CHRO). Returns a structured, audited deliverable. Reference case: Pennylane (180 FTE) — Catalogue 8 formations · 3 parcours individuels · ROI €480k · Payback 7 mois. Inputs are validated server-side — send the documente...
This record as markdown: /tools/io-github-getgapup-mcp-knowledge/ld-architect.md
What ld_architect does on Mcp Knowledge
AI agents call ld_architect to retrieve information from Mcp Knowledge without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
team | object | Yes | |
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 |
budget | object | Yes | |
company | object | Yes | |
learningNeeds | array | Yes |
Parameters from the server's own tool schema.
Why ld_architect is rated Low
The tool appears to generate structured deliverables related to learning & development architecture (training catalogues, individual paths, ROI analysis). This is fundamentally a content generation/analysis tool that reads inputs and returns structured outputs. No evidence of writing to external systems, executing code, or financial transactions.
From the tool's definition 'Architecte formation & développement' — Returns a structured, audited deliverable' — describes generating a structured analysis/plan document (training catalogue, individual paths, ROI calculation)
Risk signalsHigh parameter count (15 properties)
Attacks that exploit this kind of access
The rule that runs ld_architect 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 ld_architect, this is the rule to start with:
ld_architect is read-only, so it stays allowed. 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 ld_architect call is checked against it from then on.
Questions about ld_architect
Architecte formation & développement — Gapup agent-payable C-suite expertise (CHRO). Returns a structured, audited deliverable. Reference case: Pennylane (180 FTE) — Catalogue 8 formations · 3 parcours individuels · ROI €480k · Payback 7 mois. Inputs are validated server-side — send the documented case fields. It is categorised as a Read tool in the Mcp Knowledge MCP Server, which means it retrieves data without modifying state.
ld_architect accepts 5 parameters: team, async, budget, company, learningNeeds. Required: team, budget, company, learningNeeds. 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 ld_architect: 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.
ld_architect is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ld_architect 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 ld_architect. 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.
ld_architect 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.
This server
Across the catalogue