inspect_variables
Inspects variables in a BP5 file, returning type, shape, and steps. Optionally filters by variable name.
This record as markdown: /tools/io-github-iowarp-adios-mcp/inspect-variables.md
What inspect_variables does on CLIO Adios
AI agents call inspect_variables to retrieve information from CLIO Adios without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why inspect_variables is rated Low
The tool queries metadata and variable information from scientific data files without performing writes, deletions, execution of arbitrary code, or financial operations. The optional filtering by variable name further confirms this is a lookup/inspection utility. Blast radius is minimal—misuse would only expose data already accessible via the file system.
From the tool's definition Tool description states 'Inspects variables in a BP5 file, returning type, shape, and steps'—this is purely data retrieval with no modification or side effects. The term 'Inspects' combined with 'returning' indicates read-only query functionality.
Attacks that exploit this kind of access
The rule that runs inspect_variables safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CLIO Adios, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For inspect_variables, this is the rule to start with:
inspect_variables is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect CLIO Adios, apply this rule, and every inspect_variables call is checked against it from then on.
Questions about inspect_variables
Inspects variables in a BP5 file, returning type, shape, and steps. Optionally filters by variable name. It is categorised as a Read tool in the CLIO Adios MCP Server, which means it retrieves data without modifying state.
Register the CLIO Adios MCP server in PolicyLayer and add a rule for inspect_variables: 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 CLIO Adios. Nothing to install.
inspect_variables 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 inspect_variables 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 inspect_variables. 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.
inspect_variables is provided by the CLIO Adios MCP server (pypi:clio-kit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CLIO Adios, and thousands of servers like it.
This server
Across the catalogue