Skip to content

Add MCP tools for creating agents and prompts#633

Draft
nickmisasi wants to merge 4 commits intoMM-65671from
cursor/expose-agent-prompt-tools-b8a5
Draft

Add MCP tools for creating agents and prompts#633
nickmisasi wants to merge 4 commits intoMM-65671from
cursor/expose-agent-prompt-tools-b8a5

Conversation

@nickmisasi
Copy link
Copy Markdown
Collaborator

@nickmisasi nickmisasi commented Apr 17, 2026

Summary

  • add embedded Mattermost MCP tools for getting, creating, and updating self-serve agents
  • add embedded Mattermost MCP tools for getting, creating, and updating custom prompts
  • keep updates LLM-friendly by resolving service/name lookups and merging partial changes into the plugin's full-object REST contracts
  • cover the plugin-route bridge and discovery behavior with focused Go tests

Testing

  • go test ./mcpserver/tools -run 'TestTool(ListAgentsAndGetAgentUsePluginRoutes|ListCustomPromptsAndGetCustomPromptUsePluginRoutes|CreateAgentUsesPluginRoutes|UpdateAgentMergesExistingState|CreateAndUpdateCustomPromptUsePluginRoutes)$'
  • go test ./mcpserver/tools ./mcp
  • go test ./mcpserver/... ./mcp/... (still fails in this environment because existing mcpserver integration tests require rootless Docker/Testcontainers)

Walkthrough

mcp_agent_prompt_tools_tests.log
mcp_read_tools_tests.log
mcp_ci_fix_tests.log
mcp_govet_fix_tests.log
mcp_full_test_warning.log

Open in Web Open in Cursor 

Co-authored-by: Nick Misasi <nick13misasi@gmail.com>
@github-actions
Copy link
Copy Markdown

github-actions bot commented Apr 17, 2026

🤖 LLM Evaluation Results

OpenAI

⚠️ Overall: 18/19 tests passed (94.7%)

Provider Total Passed Failed Pass Rate
⚠️ OPENAI 19 18 1 94.7%

❌ Failed Evaluations

Show 1 failures

OPENAI

1. TestReactEval/[openai]_react_cat_message

  • Score: 0.00
  • Rubric: The word/emoji is a cat emoji or a heart/love emoji
  • Reason: The output is the text "smiley_cat", which is not a cat emoji (e.g., 🐱/😺) nor a heart/love emoji (e.g., ❤️/💕).

Anthropic

Overall: 19/19 tests passed (100.0%)

Provider Total Passed Failed Pass Rate
✅ ANTHROPIC 19 19 0 100.0%

This comment was automatically generated by the eval CI pipeline.

cursoragent and others added 3 commits April 17, 2026 17:44
Co-authored-by: Nick Misasi <nick13misasi@gmail.com>
Co-authored-by: Nick Misasi <nick13misasi@gmail.com>
Co-authored-by: Nick Misasi <nick13misasi@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants