diff --git a/README.md b/README.md
index e39c8c1..3ccc164 100644
--- a/README.md
+++ b/README.md
@@ -103,6 +103,13 @@ npm run inspector
 
 This will start a server where you can access debugging tools directly in your browser.
 
+## Running evals
+
+The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentation can be found [here](https://www.mcpevals.io/docs).
+
+```bash
+OPENAI_API_KEY=your-key  npx mcp-eval src/evals/evals.ts src/server.ts
+```
 ## YepCode MCP Tools Reference
 
 The MCP server provides several tools to interact with YepCode's infrastructure:
diff --git a/package.json b/package.json
index 92911db..150117e 100644
--- a/package.json
+++ b/package.json
@@ -52,7 +52,8 @@
     "@modelcontextprotocol/sdk": "^1.10.1",
     "@yepcode/run": "^1.2.1",
     "dotenv": "^16.4.7",
-    "zod": "^3.24.2"
+    "zod": "^3.24.2",
+    "mcp-evals": "^1.0.18"
   },
   "devDependencies": {
     "@types/node": "^22",
@@ -60,4 +61,4 @@
     "typescript": "^5.3.2"
   },
   "types": "dist/index.d.ts"
-}
+}
\ No newline at end of file
diff --git a/src/evals/evals.ts b/src/evals/evals.ts
new file mode 100644
index 0000000..701f863
--- /dev/null
+++ b/src/evals/evals.ts
@@ -0,0 +1,59 @@
+//evals.ts
+
+import { EvalConfig } from 'mcp-evals';
+import { openai } from "@ai-sdk/openai";
+import { grade, EvalFunction } from "mcp-evals";
+
+const run_codeEval: EvalFunction = {
+  name: "run_code Tool Evaluation",
+  description: "Evaluates the functionality of the run_code tool",
+  run: async () => {
+    const result = await grade(openai("gpt-4"), "Please write a Python script that uses the requests library to fetch the latest exchange rates from a public API that is not integrated with existing tools. Parse the JSON response and print out the currency symbol and the exchange rate for USD, EUR, and GBP. Then run the code in your secure environment and provide the output.");
+    return JSON.parse(result);
+  }
+};
+
+const set_env_varEval: EvalFunction = {
+  name: "set_env_var Tool Evaluation",
+  description: "Evaluates if an environment variable was correctly set",
+  run: async () => {
+    const result = await grade(openai("gpt-4"), "Please set the environment variable 'MY_TEST_VAR' to the value 'test123'. Confirm that it has been successfully set.");
+    return JSON.parse(result);
+  }
+};
+
+const remove_env_varEval: EvalFunction = {
+  name: "remove_env_var Tool Evaluation",
+  description: "Evaluates removing a YepCode environment variable",
+  run: async () => {
+    const result = await grade(openai("gpt-4"), "Please remove the environment variable named 'MY_SECRET_KEY' from my YepCode environment.");
+    return JSON.parse(result);
+  }
+};
+
+const get_executionEval: EvalFunction = {
+    name: 'get_execution Tool Evaluation',
+    description: 'Evaluates the accuracy and completeness of get_execution tool usage',
+    run: async () => {
+        const result = await grade(openai("gpt-4"), "Could you retrieve the logs and status from a YepCode job with the ID 12345?");
+        return JSON.parse(result);
+    }
+};
+
+const run_ycp_processEval: EvalFunction = {
+  name: 'run_ycp_processEval',
+  description: 'Evaluates the correctness of the run_ycp_process tool functionality',
+  run: async () => {
+    const result = await grade(openai("gpt-4"), "Please run the process named 'testProcess' with parameters {\"param1\":\"value1\",\"param2\":42} and return the outcome.");
+    return JSON.parse(result);
+  }
+};
+
+const config: EvalConfig = {
+    model: openai("gpt-4"),
+    evals: [run_codeEval, set_env_varEval, remove_env_varEval, get_executionEval, run_ycp_processEval]
+};
+  
+export default config;
+  
+export const evals = [run_codeEval, set_env_varEval, remove_env_varEval, get_executionEval, run_ycp_processEval];
\ No newline at end of file