AI agents call synaptex_list to retrieve information from Synaptex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval tool that queries and returns information about existing projects and their metadata. It has no side effects, cannot modify or delete data, and does not execute code or trigger external operations. The French description 'Liste tous les projets' confirms it is simply listing/enumerating existing resources.
From the tool's definition Tool name and description indicate it 'lists all projects synced from Forgejo with their detected stack' — a read-only enumeration operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Liste tous les projets synced depuis Forgejo avec leur stack détectée. It is categorised as a Read tool in the Synaptex MCP Server, which means it retrieves data without modifying state.
Register the Synaptex MCP server in PolicyLayer and add a rule for synaptex_list: 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 Synaptex. Nothing to install.
synaptex_list 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 synaptex_list 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 synaptex_list. 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.
synaptex_list is provided by the Synaptex MCP server (jeromelabophy-gif/synaptex_claude). 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 →