Skip to content
POST/api/v1/mcp-test

Run quick MCP test

Exercises a caller-supplied list of MCP tool definitions against a caller-supplied MCP `endpoint`. Body requires `tools[]` (each with `name`, `description`, `inputSchema`) and `endpoint` (a valid URL); the route does NOT discover tools or resources from the server — it invokes only the tools you pass. Each invocation is a POST of `{tool, arguments}` through the SSRF guard (`safeFetch` rejects RFC1918/CGNAT/link-local/loopback and cloud-metadata targets, and follows redirects itself — up to 5 hops, re-validating every hop against the guard and stripping secret-bearing headers cross-origin — rather than letting fetch follow them blindly). Optional `options`: `maxLatencyMs` (default 5000), `testSchemaValidation` (default true), `testErrorHandling` (default true), `testInjection` (default false). Synchronous — returns per-tool results plus a summary `{totalTools, totalPassed, totalFailed, totalTests, passRate}`.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Response

200 example

{
  "success": true
}

All status codes

200Test result.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
429(no description)
500Internal Server Error — MCP_TEST_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/mcp-test \
  -H "Authorization: Bearer $EVALGUARD_API_KEY"

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/mcp-test", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}` },
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}

response = requests.request("POST", "https://evalguard.ai/api/v1/mcp-test", headers=headers)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
)

func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/mcp-test", nil)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403429500

Other Evals endpoints