feat(mcp): implement dynamic MCP servers configuration system#85
Closed
chambridge wants to merge 209 commits intoambient-code:mainfrom
Closed
feat(mcp): implement dynamic MCP servers configuration system#85chambridge wants to merge 209 commits intoambient-code:mainfrom
chambridge wants to merge 209 commits intoambient-code:mainfrom
Conversation
…oject-documentation-structure-154e Maintain project documentation structure
…ed scripts and documentation. Enhance project setup with updated dependencies and installation instructions in README. Ensure clarity in project organization for future development.
Fix docker compose deployment mode and revise first stage
…pdate command-line interface to support soft and hard modes for Jira ticket generation. Improve logging and validation processes for generated ticket structures.
…as-stage implement draft Jiras stage
…s for various external API providers. Introduce a deployment script for easier configuration and setup. Update README to reflect new deployment options and link to detailed guides.
Added additional guidance to Soft Mode instructions including sizing guidelines and cross-ticket dependency guidelines
…integration. Add MCP Atlassian URL to .env.example, enhance deploy-to-openshift.sh with new secrets, and modify openshift-deployment.yaml to include Jira MCP service and deployment. Refactor llama_stack_setup.py to utilize environment variables for configuration. Improve logging for toolgroup registration process.
…ncluding Kubernetes deployment, service, and route definitions in openshift-deployment.yaml. Update pyproject.toml and uv.lock to include new dependencies: sqlalchemy, psycopg2-binary, and pydantic. Modify llama_stack_setup.py to use CONFIGURE_TOOLGROUPS environment variable for toolgroup configuration.
Deployment on openshift and api creation
Update draft_jiras.md
Added Ticket Sizing table with data from 2025 sprint history to add context to estimating team-specific story point sizing using team's Average duration per story point from the table.
Update draft_jiras.md - Added Ticket Sizing Table
…lity. Update `openshift-deployment.yaml` to switch vector provider from Milvus to Faiss, adjust database paths, and add a command for the server container. Modify `pyproject.toml` to include `uvicorn` with standard extras and add new dependencies in `uv.lock`. Implement WebSocket management in the API for real-time session updates, including a new `WebSocketManager` class and related endpoint. Update message handling in the API models and schemas to incorporate message status tracking.
…oint for JIRA metrics to retrieve comprehensive metrics for a JIRA issue and its children. Updated deployment scripts and configuration to support PostgreSQL database integration. Removed outdated contributing and custom API examples documentation. Updated frontend components to include new settings and metrics features.
…ove frontend components. Added GitHub access token to .env.example for Llama Index setup. Updated OpenShift deployment configuration to include new providers and tool groups. Enhanced package dependencies in pyproject.toml and uv.lock for improved functionality. Updated frontend package-lock.json and package.json to include the latest PatternFly components. Refactored session management in frontend components to support new RAG features and improved UI navigation.
…selection functionality. Added a new button in AppLayout for navigating to the RAG page. Updated SessionSidebar to manage vector database selections, including loading available databases and displaying selected ones in a dropdown. Modified related types and API endpoints to support vector database IDs in session management.
…eamline layout and improve loading/error handling. Removed unnecessary Panel components and integrated Flex for better responsiveness. Added chat message functionality in SessionManager with API integration for sending messages. Updated API service to handle chat message requests and responses, enhancing user interaction within the session.
…various frontend components. Update environment setup to include dotenv for loading environment variables. Refactor main application structure by eliminating unused files and enhancing the overall project organization.
Bumps [actions/add-to-project](https://github.com/actions/add-to-project) from 0.5.0 to 1.0.2. - [Release notes](https://github.com/actions/add-to-project/releases) - [Commits](actions/add-to-project@v0.5.0...v1.0.2) --- updated-dependencies: - dependency-name: actions/add-to-project dependency-version: 1.0.2 dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>
Bumps [actions/checkout](https://github.com/actions/checkout) from 4 to 5. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](actions/checkout@v4...v5) --- updated-dependencies: - dependency-name: actions/checkout dependency-version: '5' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>
Bumps [actions/github-script](https://github.com/actions/github-script) from 6 to 7. - [Release notes](https://github.com/actions/github-script/releases) - [Commits](actions/github-script@v6...v7) --- updated-dependencies: - dependency-name: actions/github-script dependency-version: '7' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>
…ctions/actions/add-to-project-1.0.2 Bump actions/add-to-project from 0.5.0 to 1.0.2
…actions/actions/checkout-5 Bump actions/checkout from 4 to 5
…actions/actions/github-script-7 Bump actions/github-script from 6 to 7
…-configs Add vTeam shared Claude Code configuration with hooks-based enforcement
…LI commands and documentation to reflect changes in RAG store usage. Enhance frontend components with new session management features, including real-time updates and improved chat functionality. Update API service to support new session update endpoints and document ingestion methods.
Signed-off-by: Ryan Cook <rcook@redhat.com>
Signed-off-by: Ryan Cook <rcook@redhat.com>
rename of file and add deploy action
Signed-off-by: Ryan Cook <rcook@redhat.com>
login should be token only not server
…login_change Revert "login should be token only not server"
Need to provide ns
🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add missing Radix UI dependencies for new UI components with correct versions: - @radix-ui/react-checkbox: ^1.3.3 - @radix-ui/react-progress: ^1.1.7 - @radix-ui/react-tabs: ^1.1.13 - @radix-ui/react-toast: ^1.2.15 - Add react-resizable-panels: ^3.0.6 for resizable editor interface - Update claude-code-runner Dockerfile to include agent files 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add Git configuration management from .env variables - Update env.example with Git settings for RFE workflows - Add RFE-specific deployment messaging and next steps - Support dynamic git-configmap updates during deployment 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Added complete RFE workflow management with:
- RFE workflow data structures and models
- CRUD operations (create, read, update, delete workflows)
- Phase management (specify -> plan -> tasks -> completed)
- Artifact management for file editing interface
- Git integration endpoints (push to repository)
- Agent session tracking within workflows
- In-memory storage (TODO: implement persistent storage)
API endpoints implemented:
- GET/POST /api/rfe-workflows
- GET/DELETE /api/rfe-workflows/:id
- POST /api/rfe-workflows/:id/{pause,resume,advance-phase,push-to-git}
- GET/PUT /api/rfe-workflows/:id/artifacts/*path
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Created frontend proxy routes that mirror backend RFE workflow endpoints: - /api/rfe-workflows (GET, POST) - List and create workflows - /api/rfe-workflows/[id] (GET, DELETE) - Individual workflow operations - /api/rfe-workflows/[id]/pause (POST) - Pause workflow - /api/rfe-workflows/[id]/resume (POST) - Resume workflow - /api/rfe-workflows/[id]/advance-phase (POST) - Advance phase - /api/rfe-workflows/[id]/push-to-git (POST) - Push to repository - /api/rfe-workflows/[id]/artifacts/[...path] (GET, PUT) - Artifact editing Fixes 404 errors from frontend by providing proper API proxy layer. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
🔧 Data Structure Fixes: - Fixed frontend-backend data mismatch (targetRepository vs targetRepoUrl/targetRepoBranch) - Updated TypeScript types to match Go backend structs exactly - Fixed form submission to send correct JSON structure 🛡️ Error Handling Improvements: - Added try-catch blocks to agent selection functions - Enhanced Clear All button safety with error boundaries - Improved handleAgentToggle error handling 📊 Backend Logging Enhancements: - Added detailed validation error logging - Success logging with workflow details - Better debugging information for 400 errors Co-Authored-By: Claude <noreply@anthropic.com>
Signed-off-by: Ryan Cook <rcook@redhat.com>
Signed-off-by: Ryan Cook <rcook@redhat.com>
Signed-off-by: Ryan Cook <rcook@redhat.com>
old artifacts we arent using anymore
…builds adding macos image builds
- Change from merge ref to PR head ref for proper review context - Add repository and token parameters for cross-fork PR support - Ensures Claude Code reviews against actual PR changes 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
WIP: UI functionality as well as agent functions
…view-workflow fix: Update Claude Code review workflow to checkout PR head
Collaborator
|
lgtm |
Add comprehensive MCP server configuration management for Claude Code runner:
- Add dynamic MCP configuration loading from /app/.mcp.json with fallback to defaults
- Create mcp-servers-configmap.yaml for Kubernetes ConfigMap integration
- Update deploy.sh to support --atlassian-mcp-url parameter with SSE schema validation
- Enhance startup logging to display loaded MCP servers before API key validation
- Refactor _load_mcp_servers_config() as static method for cleaner architecture
- Remove hardcoded "Playwright MCP" references to support generic MCP servers
- Add proper SSE MCP server schema support: {"type": "sse", "url": "..."}
This enables dynamic configuration of both command-based (playwright) and
SSE-based (atlassian-mcp) MCP servers via Kubernetes ConfigMaps, improving
flexibility and maintainability of the agentic runner system.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Signed-off-by: Chris Hambridge <chambrid@redhat.com>
b260b1f to
14fc372
Compare
Collaborator
|
@chambridge closing and please re-open if you'd like to keep it. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add comprehensive MCP server configuration management for Claude Code runner:
This enables dynamic configuration of both command-based (playwright) and SSE-based (atlassian-mcp) MCP servers via Kubernetes ConfigMaps, improving flexibility and maintainability of the agentic runner system.