search_charities
Search the charity registry by free-text name. Returns up to limit matches, each with slug, name, country, city/state, foundation_type, integrity_score, and the canonical page URL. Use this BEFORE resources/read when the user names a charity but you don't know its slug. The match is case-insensit...
This record as markdown: /tools/com-giveradar-charity-registry/search-charities.md
What search_charities does on Charity Registry
AI agents call search_charities to retrieve information from Charity Registry without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | |
query | string | Yes | Name search query, 2+ chars. |
country | string | — | Optional ISO 3166-1 alpha-2 country filter (e.g. 'ID', 'NL'). |
Parameters from the server's own tool schema.
Why search_charities is rated Low
This tool retrieves and queries charity data without side effects. It is a search operation that returns matching records from a read-only registry. There is no capability to modify, delete, or execute external operations. The blast radius of misuse is minimal—an agent could only retrieve information about charities that is already publicly available in the registry.
From the tool's definition Tool performs "Search the charity registry by free-text name" and "Returns up to `limit` matches" with read-only data fields (slug, name, country, city/state, foundation_type, integrity_score, URL). No modification, deletion, or execution of operations.
Attacks that exploit this kind of access
The rule that runs search_charities safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Charity Registry, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search_charities, this is the rule to start with:
search_charities 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 Charity Registry, apply this rule, and every search_charities call is checked against it from then on.
Questions about search_charities
Search the charity registry by free-text name. Returns up to limit matches, each with slug, name, country, city/state, foundation_type, integrity_score, and the canonical page URL. Use this BEFORE resources/read when the user names a charity but you don't know its slug. The match is case-insensitive substring on the charity's name. It is categorised as a Read tool in the Charity Registry MCP Server, which means it retrieves data without modifying state.
search_charities accepts 3 parameters: limit, query, country. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Charity Registry MCP server in PolicyLayer and add a rule for search_charities: 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 Charity Registry. Nothing to install.
search_charities 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 search_charities 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 search_charities. 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.
search_charities is provided by the Charity Registry MCP server (https://giveradar.com/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Charity Registry, and thousands of servers like it.
This server
Across the catalogue