Resolve a research organization via the Research Organization Registry (ROR). Pass id (a ROR id) or name (free-text search). Returns canonical ROR id, name, type, location (GeoNames), website, external ids (GRID/ISNI/Wikidata/Fundref), relationships, and aliases. Free, CC0. The canonical institut...
AI agents call research.org to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the Research Organization Registry (ROR) to retrieve institutional metadata. It performs a straightforward lookup operation with no side effects—it neither modifies data, executes code, triggers external actions, nor involves financial transactions. The blast radius of misuse is minimal; an agent might retrieve unwanted metadata or spam the service, but cannot alter or delete records.
From the tool's definition Tool description explicitly states it 'Resolve[s]' and 'Returns' data from a registry. Verbs are retrieval-focused: 'Pass id or name', 'Returns canonical ROR id, name, type, location...' No modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Resolve a research organization via the Research Organization Registry (ROR). Pass id (a ROR id) or name (free-text search). Returns canonical ROR id, name, type, location (GeoNames), website, external ids (GRID/ISNI/Wikidata/Fundref), relationships, and aliases. Free, CC0. The canonical institution key in scholarly metadata. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for research.org: 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 Mcp. Nothing to install.
research.org 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 research.org 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 research.org. 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.
research.org is provided by the MCP server (@2sio/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 →