🚀 [STEP 5/5: SERVE] Start a local development server for testing a project. PREREQUISITES: - project_create must have been run - project_add_source must have added at least one source - project_build must have processed sources into chunks/vectors - project_export must have generated the server ...
AI agents invoke indexfoundry_project_serve to trigger actions in IndexFoundry MCP. 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.
This tool executes arbitrary operations on the system including installing dependencies and starting a server process. While not destructive or financial, it goes beyond read/write to actively run external commands and processes. The npm install operation in particular can execute scripts and install arbitrary packages, making this an Execute-category tool.
From the tool's definition Tool starts a local development server and runs npm install - executes code on the user's system. Description states it 'Start[s] a local development server for testing' and 'runs npm install if needed', which are code execution operations.
Attacks that exploit this kind of access
🚀 [STEP 5/5: SERVE] Start a local development server for testing a project. PREREQUISITES: - project_create must have been run - project_add_source must have added at least one source - project_build must have processed sources into chunks/vectors - project_export must have generated the server code WHAT THIS DOES: 1. Checks if dependencies are installed (runs npm install if needed) 2. For mode=. It is categorised as a Execute tool in the IndexFoundry MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the IndexFoundry MCP server in PolicyLayer and add a rule for indexfoundry_project_serve: 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 IndexFoundry MCP. Nothing to install.
indexfoundry_project_serve 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 indexfoundry_project_serve 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 indexfoundry_project_serve. 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.
indexfoundry_project_serve is provided by the IndexFoundry MCP server (mnehmos/mnehmos.index-foundry.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →