
GiveRadar MCP server
Which MCP servers are GiveRadar's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-21
- Registry namecom.giveradar/charity-registryverified in the MCP registry
The registry name sits under giveradar.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools4
- Server calls itselfgiveradar-mcp
- Server version1.0.0
- Protocol version2024-11-05
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 310 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- Parameters are untyped or undescribed in 2 of 4 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score85 of 100answers 100 · definitions 92 · context 100 · use 0 · connects 100
- Answered100% of days8 of 8 daily checks
- Median first answer639 ms
- Space in an agent's context≈ 570 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 92 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 4
What an agent can do with it
- not sure · Verify a charity's registration and finances before donating
- not sure · Assess a prospective grantee's record across borders
- not sure · Cite official registry data in research on nonprofits
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_charitiesSearch 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…
compare_charitiesSide-by-side comparison of 2-5 charities by slug. Returns their integrity scores, program/admin/fundraising ratios, annual revenue, founding year, foundation type, and a deterministic verdict on which has the strongest transparency…
find_similarGiven one charity's slug, return up to `limit` other charities in the same country + category. Useful for 'find more like this' recommendations. Excludes the input charity from the result.
verify_charityLook up a charity by its official registry identifier - EIN (US), Charity Commission number (GB), RSIN (NL), AHU/Kemenkumham reg number (ID), or a generic registration_number for other countries. Returns the matched charity or null. Use…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"charity-registry": {
"type": "http",
"url": "https://giveradar.com/mcp/"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http giveradar https://giveradar.com/mcp/claude.ai, ChatGPT and other clients: add https://giveradar.com/mcp/ as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.