Search using CMIS SQL syntax. Default query searches for PDF documents.
AI agents invoke cmis_search to trigger actions in Alfresco MCP Server. 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.
Although primarily a read/search operation, accepting arbitrary CMIS SQL syntax elevates this beyond a simple Read tool into Execute territory, as the query language can be crafted to extract sensitive content, enumerate repository structure, or potentially trigger server-side operations depending on the CMIS implementation.
From the tool's definition Search using CMIS SQL syntax — executes arbitrary SQL-like queries against the repository. While default behavior searches for PDFs, the tool accepts custom CMIS SQL which could be used to probe sensitive metadata or structure.
Documented attack patterns abuse exactly the kind of access cmis_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Alfresco MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cmis_search:
{
"version": "1",
"default": "deny",
"tools": {
"cmis_search": {
"limits": [
{
"counter": "cmis_search_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} cmis_search 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.
Free to start. No card required.
Search using CMIS SQL syntax. Default query searches for PDF documents. It is categorised as a Execute tool in the Alfresco MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Alfresco MCP Server MCP server in PolicyLayer and add a rule for cmis_search: 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 Alfresco MCP Server. Nothing to install.
cmis_search 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 cmis_search 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 cmis_search. 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.
cmis_search is provided by the Alfresco MCP Server MCP server (stevereiner/python-alfresco-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Alfresco MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Alfresco MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.