Bounded timeseries for an entity: price, macro_series, or etf_flows. Returns points oldest-first with an explicit downsampling flag when the raw series exceeded max_points. etf_flows is filing-cadence (one point per SEC filing refresh), NOT per calendar day, so even a wide window yields a handful...
AI agents call get_timeseries to retrieve information from Sugra API without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
entity | object | Yes | |
metric | string | Yes | |
max_points | integer | — | |
granularity | string | — |
Parameters from the server's own tool schema.
This is a straightforward data retrieval tool that queries historical timeseries data bounded by entity and time parameters. It has no side effects—it only reads and returns existing data points. The 'Costs 1 unit per call' indicates metering but not financial transaction capability. No code execution, no data modification, and no destructive operations are possible.
From the tool's definition Tool description states it 'Returns points oldest-first' for timeseries data (price, macro_series, etf_flows). No modification, deletion, or execution of external operations described. Parameters are all inputs for querying/filtering existing data.
Attacks that exploit this kind of access
Bounded timeseries for an entity: price, macro_series, or etf_flows. Returns points oldest-first with an explicit downsampling flag when the raw series exceeded max_points. etf_flows is filing-cadence (one point per SEC filing refresh), NOT per calendar day, so even a wide window yields a handful of points. Times are UTC. Costs 1 unit per call. Args: metric: One of price / macro_series / etf_flows. entity: Entity dict from resolve_entity ({"namespace": ..., "ids": ...}). granularity: Requested point granularity (default "1d"). max_points: Hard cap on returned points (default 500). It is categorised as a Read tool in the Sugra API MCP Server, which means it retrieves data without modifying state.
get_timeseries accepts 4 parameters: entity, metric, max_points, granularity. Required: entity, metric. The full parameter table on this page comes from the server's own tool schema.
Register the Sugra API MCP server in PolicyLayer and add a rule for get_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 Sugra API. Nothing to install.
get_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 get_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 get_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.
get_timeseries is provided by the Sugra API MCP server (pypi:sugra-api-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 →