diff --git a/plugin/.mcp.json b/plugin/.mcp.json
index 3466664d1..b5ae1a6cc 100644
--- a/plugin/.mcp.json
+++ b/plugin/.mcp.json
@@ -4,10 +4,6 @@
       "command": "npx",
       "args": ["-y", "@azure/mcp@latest", "server", "start"]
     },
-    "foundry-mcp": { 
-      "type": "http", 
-      "url": "https://mcp.ai.azure.com" 
-    },
     "context7": {
       "command": "npx",
       "args": ["-y", "@upstash/context7-mcp@latest"]
diff --git a/plugin/skills/microsoft-foundry/SKILL.md b/plugin/skills/microsoft-foundry/SKILL.md
index 23bd44c5c..7c2eec70f 100644
--- a/plugin/skills/microsoft-foundry/SKILL.md
+++ b/plugin/skills/microsoft-foundry/SKILL.md
@@ -4,7 +4,7 @@ description: "Deploy, evaluate, and manage Foundry agents end-to-end: Docker bui
 license: MIT
 metadata:
   author: Microsoft
-  version: "1.0.3"
+  version: "1.0.4"
 ---
 
 # Microsoft Foundry Skill
diff --git a/plugin/skills/microsoft-foundry/foundry-agent/observe/observe.md b/plugin/skills/microsoft-foundry/foundry-agent/observe/observe.md
index c29f4ac88..597e0493a 100644
--- a/plugin/skills/microsoft-foundry/foundry-agent/observe/observe.md
+++ b/plugin/skills/microsoft-foundry/foundry-agent/observe/observe.md
@@ -1,6 +1,6 @@
 # Agent Observability Loop
 
-Orchestrate the full eval-driven optimization cycle for a Foundry agent. This skill manages the **multi-step workflow** — auto-creating evaluators, generating test datasets, running batch evals, clustering failures, optimizing prompts, redeploying, and comparing versions. Use this skill instead of calling individual foundry-mcp evaluation tools manually.
+Orchestrate the full eval-driven optimization cycle for a Foundry agent. This skill manages the **multi-step workflow** — auto-creating evaluators, generating test datasets, running batch evals, clustering failures, optimizing prompts, redeploying, and comparing versions. Use this skill instead of calling individual `azure` MCP evaluation tools manually.
 
 ## When to Use This Skill
 
@@ -12,7 +12,7 @@ USE FOR: evaluate my agent, run an eval, test my agent, check agent quality, run
 
 | Property | Value |
 |----------|-------|
-| MCP server | `foundry-mcp` |
+| MCP server | `azure` |
 | Key MCP tools | `evaluation_agent_batch_eval_create`, `evaluator_catalog_create`, `evaluation_comparison_create`, `prompt_optimize`, `agent_update` |
 | Prerequisite | Agent deployed and running (use [deploy skill](../deploy/deploy.md)) |
 
diff --git a/tests/microsoft-foundry/foundry-agent/observe/unit.test.ts b/tests/microsoft-foundry/foundry-agent/observe/unit.test.ts
index 9a348db11..bc19d8a34 100644
--- a/tests/microsoft-foundry/foundry-agent/observe/unit.test.ts
+++ b/tests/microsoft-foundry/foundry-agent/observe/unit.test.ts
@@ -71,7 +71,7 @@ describe("observe - Unit Tests", () => {
 
     test("contains Quick Reference table", () => {
       expect(observeContent).toContain("## Quick Reference");
-      expect(observeContent).toContain("foundry-mcp");
+      expect(observeContent).toContain("azure");
     });
   });