AI agents invoke query_osm_postgres to trigger actions in OSM PostgreSQL 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.
The tool name suggests it runs queries against a PostgreSQL database containing OpenStreetMap data. SQL queries can range from simple reads to destructive operations (DROP, DELETE, UPDATE). With an empty description, the full scope is unknown, but the ability to execute arbitrary SQL against a database warrants an 'Execute' classification with high severity due to potential for data modification or destruction.
From the tool's definition Tool name 'query_osm_postgres' implies executing queries against a PostgreSQL database; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access query_osm_postgres gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OSM PostgreSQL Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query_osm_postgres:
{
"version": "1",
"default": "deny",
"tools": {
"query_osm_postgres": {
"limits": [
{
"counter": "query_osm_postgres_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}query_osm_postgres 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.
query_osm_postgres. It is categorised as a Execute tool in the OSM PostgreSQL Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OSM PostgreSQL Server MCP server in PolicyLayer and add a rule for query_osm_postgres: 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 OSM PostgreSQL Server. Nothing to install.
query_osm_postgres 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 query_osm_postgres 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 query_osm_postgres. 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.
query_osm_postgres is provided by the OSM PostgreSQL Server MCP server (wiseman/osm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 OSM PostgreSQL Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 OSM PostgreSQL Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.