Query historical or live sensor data for one or more points. Points are identified by their timeseriesId (UUID). Use tacit_graphql first to find points and their timeseriesId values. Args: - site_id (string, required): The site ID - point_ids (string, required): Comma-separated timeseriesId UUIDs...
AI agents call tacit_timeseries to retrieve information from Tacit MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches historical or real-time sensor readings from a building digital twin. It only reads data (sensor values indexed by UUID and time range) and has no write, execute, or destructive capabilities. Misuse is limited to data exposure, making severity low.
From the tool's definition "Query historical or live sensor data for one or more points" — purely retrieves time-series data with no mention of modification or side effects
Attacks that exploit this kind of access
Query historical or live sensor data for one or more points. Points are identified by their timeseriesId (UUID). Use tacit_graphql first to find points and their timeseriesId values. Args: - site_id (string, required): The site ID - point_ids (string, required): Comma-separated timeseriesId UUIDs (max 200) - start (string, optional): Start time, relative like. It is categorised as a Read tool in the Tacit MCP MCP Server, which means it retrieves data without modifying state.
Register the Tacit MCP server in PolicyLayer and add a rule for tacit_timeseries: 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 Tacit MCP. Nothing to install.
tacit_timeseries 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 tacit_timeseries 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 tacit_timeseries. 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.
tacit_timeseries is provided by the Tacit MCP server (ucl-sbde/tacit-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 →