run_spi_table
AI agents invoke run_spi_table to trigger actions in DMAP-AI 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.
The 'run_' prefix pattern is consistent with all sibling tools on this server (run_drought_periodicity_analysis, run_drought_severity_events, run_wavelet_scalogram), which are all execution-type tools that trigger analyses. 'run_spi_table' likely executes an SPI (Standardized Precipitation Index) computation and generates a results table using external data sources (NASA POWER or ERA5-Land/CDS).
From the tool's definition Tool name 'run_spi_table' and server context 'drought monitoring and SPI drought analysis using NASA POWER and ERA5-Land/CDS data'; description is empty.
Attacks that exploit this kind of access
run_spi_table. It is categorised as a Execute tool in the DMAP-AI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DMAP-AI MCP Server MCP server in PolicyLayer and add a rule for run_spi_table: 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 DMAP-AI MCP Server. Nothing to install.
run_spi_table 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 run_spi_table 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 run_spi_table. 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.
run_spi_table is provided by the DMAP-AI MCP Server MCP server (sohrab4748/dmap-ai-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 →