farhoodlabs/devcontainer
8
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases 39 Wiki Activity

feat: add Fetch and Sequential Thinking MCP sidecars #45

Merged
cpfarhood merged 1 commits from feature/add-fetch-sequential-thinking-mcp into main 2026-02-23 18:41:47 +00:00
Conversation 0 Commits 1 Files Changed 5
+96 -2
cpfarhood commented 2026-02-23 18:37:30 +00:00 (Migrated from github.com)
Copy Link
Copy Source

Summary

This PR adds two new MCP (Model Context Protocol) sidecars to enable additional AI assistant capabilities:

  • Fetch MCP: Web content fetching and HTML to markdown conversion
  • Sequential Thinking MCP: Structured thinking and problem-solving processes

Both sidecars use the official MCP Docker images and are integrated following the existing sidecar patterns.

Changes Made

🔧 Infrastructure

  • Add fetch and sequentialthinking sidecars to values.yaml with default configurations
  • Add sidecar containers to deployment.yaml template using fastmcp with SSE transport
  • Assign ports 8082 (fetch) and 8083 (sequentialthinking) following existing port allocation pattern

📡 MCP Configuration

  • Update .mcp.json to include new server endpoints:
    • http://localhost:8082/sse (fetch)
    • http://localhost:8083/sse (sequentialthinking)

📚 Documentation

  • Update CLAUDE.md MCP sidecars table with new entries
  • Add descriptive notes for both new sidecars
  • Update enable/disable examples to include new sidecars
  • Update .mcp.json description to list all available servers

Default Configuration

Both new sidecars are enabled by default with:

  • Standard resource limits (64Mi-256Mi memory, 50m-500m CPU)
  • Health checks (liveness/readiness probes)
  • SSE transport on dedicated ports

Testing

  • Validated Helm template rendering
  • Confirmed port allocations don't conflict with existing sidecars
  • Documentation examples updated for consistency

Closes

  • Closes #43 - Add the Fetch MCP as a sidecar
  • Closes #44 - Add the sequential thinking MCP

Generated with Claude Code via Happy

## Summary This PR adds two new MCP (Model Context Protocol) sidecars to enable additional AI assistant capabilities: - **Fetch MCP**: Web content fetching and HTML to markdown conversion - **Sequential Thinking MCP**: Structured thinking and problem-solving processes Both sidecars use the official MCP Docker images and are integrated following the existing sidecar patterns. ## Changes Made ### 🔧 Infrastructure - Add `fetch` and `sequentialthinking` sidecars to `values.yaml` with default configurations - Add sidecar containers to `deployment.yaml` template using `fastmcp` with SSE transport - Assign ports 8082 (fetch) and 8083 (sequentialthinking) following existing port allocation pattern ### 📡 MCP Configuration - Update `.mcp.json` to include new server endpoints: - `http://localhost:8082/sse` (fetch) - `http://localhost:8083/sse` (sequentialthinking) ### 📚 Documentation - Update `CLAUDE.md` MCP sidecars table with new entries - Add descriptive notes for both new sidecars - Update enable/disable examples to include new sidecars - Update `.mcp.json` description to list all available servers ## Default Configuration Both new sidecars are **enabled by default** with: - Standard resource limits (64Mi-256Mi memory, 50m-500m CPU) - Health checks (liveness/readiness probes) - SSE transport on dedicated ports ## Testing - Validated Helm template rendering - Confirmed port allocations don't conflict with existing sidecars - Documentation examples updated for consistency ## Closes - Closes #43 - Add the Fetch MCP as a sidecar - Closes #44 - Add the sequential thinking MCP Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering)
Sign in to join this conversation.
Reviewers
No Reviewers
Labels
Clear labels
antigravity
architecture
automation
bug
Something isn't working
 documentation
Improvements or additions to documentation
 duplicate
This issue or pull request already exists
 enhancement
New feature or request
 examples
good first issue
Good for newcomers
 helm
help wanted
Extra attention is needed
 invalid
This doesn't seem right
 maintainability
monitoring
question
Further information is requested
 refactor
tooling
user-experience
validation
wontfix
This will not be worked on
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
fl_blake (Blake MIddleware) cpfarhood (Chris Farhood) ci (Continuous Integration [bot]) flux (Flux CD) admin (Gitea Admin) fl_hugh (Hugh Commit) renovate (Mend Renovate) fl_warren (Warren Bufferpool)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: farhoodlabs/devcontainer#45
Delete Branch "feature/add-fetch-sequential-thinking-mcp"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?