MCP-Mem0

SFCore TH Dev: CumulusCI Integration for AI Agents

An implementation of theModel Context Protocol (MCP)server integrated withCumulusCIfor providing AI agents with Salesforce development capabilities.

# Check if CCI is installed cci version # Install CCI if not present pipx install cumulusci-plus-azure-devops # Upgrade CCI if needed pipx install cumulusci-plus-azure-devops --force

git clone <your-repo-url> cd sfcore-th-dev

pip install cumulusci cci org connect <your-dev-hub>

docker build -t ghcr.io/jorgesolebur/mcp-sfcore-th-dev:latest --build-arg PORT=8050 .

docker push ghcr.io/jorgesolebur/mcp-sfcore-th-dev:latest

echo $GITHUB_TOKEN | docker login ghcr.io -u jorgesolebur --password-stdin

# Set TRANSPORT=sse in .env then: uv run src/main.py

docker run -d -p 8050:8050 ghcr.io/jorgesolebur/mcp-sfcore-th-dev:latest

{ "mcpServers": { "sfcore-th-dev": { "transport": "sse", "url": "http://localhost:8050/sse" } } }

{ "mcpServers": { "sfcore-th-dev": { "transport": "sse", "serverUrl": "http://localhost:8050/sse" } } }

So the full URL in the MCP node would be:http://host.docker.internal:8050/sse

{ "mcpServers": { "sfcore-th-dev": { "command": "your/path/to/sfcore-th-dev/.venv/Scripts/python.exe", "args": ["your/path/to/sfcore-th-dev/src/main.py"], "env": { "TRANSPORT": "stdio" } } } }

{ "mcpServers": { "sfcore-th-dev": { "command": "docker", "args": ["run", "--rm", "-i", "-e", "TRANSPORT", "ghcr.io/jorgesolebur/mcp-sfcore-th-dev:latest"], "env": { "TRANSPORT": "stdio" } } } }

This template provides a foundation for building more comprehensive CCI integrations. To add new CCI tools:
- Create a new@mcp.tool()method
- Use theget_cci_command_instructions()utility function for consistent behavior
- Example:

@mcp.tool() async def deploy_to_org(org_name: str = "dev") -> str: command = f"cci flow run deploy --org {org_name}" purpose = f"Deploy to org '{org_name}'" return get_cci_command_instructions(command, purpose)

This ensures all tools have consistent command execution and error handling.

- check_cci_installation: Checks if CumulusCI is installed and provides installation/upgrade instructions

- create_dev_scratch_org: Creates a development scratch org usingcci flow run dev_org --org <org_name>
- create_feature_scratch_org: Creates a feature/QA scratch org usingcci flow run ci_feature_2gp --org <org_name>
- create_beta_scratch_org: Creates a beta/regression scratch org usingcci flow run regression_org --org <org_name>
- list_orgs: Lists all connected CumulusCI orgs usingcci org list
- open_org: Opens the specified org in a browser usingcci org browser --org <org_name>

- run_tests: Runs Apex tests in a specified org usingcci task run run_all_tests_locally --org <org_name>
- retrieve_changes: Retrieves metadata changes from the specified org usingcci task run retrieve_changes --org <org_name>
- deploy: Deploys local metadata to the specified org usingcci task run deploy --org <org_name>

- run_generic_cci_task: Handles any CCI task that doesn't have a dedicated tool following a 3-step approach:
- Checks if the task exists usingcci task list
- Gets task information and parameters usingcci task infoorcci task run --help
- Runs the task with appropriate parameters after collecting required values from the user

All CCI tools provide setup guidance if needed and follow consistent error handling patterns.

The server provides framework-specific documentation through MCP resources. These resources give agents contextual information about development practices and standards.

Access resources using the URI pattern:framework://<framework-name>

-

framework://salesforce-triggers: Comprehensive guidelines for developing Apex triggers

- Trigger framework architecture
- Handler pattern implementation
- Best practices and anti-patterns
- Testing strategies
- Performance considerations

framework://salesforce-logging: Logging standards and best practices

- Custom logger implementation
- Log levels and usage guidelines
- Performance considerations
- Production logging strategies
- Security and privacy considerations

framework://salesforce-cache-manager: Platform Cache management framework for performance optimization

- Three cache types: Organization, Session, and Transaction
- Declarative configuration with custom metadata
- Usage examples and best practices
- Performance monitoring and debugging
- Security considerations for cached data

Agents can request framework documentation when needed:

{ "method": "resources/read", "params": { "uri": "framework://salesforce-triggers" } }

This provides on-demand access to framework-specific guidance without cluttering tool descriptions.

- Additional framework resources (LWC, Aura, Flows)
- More CCI operation tools
- Integration with CI/CD pipelines
- Advanced testing workflows

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Paid remote MCP for agent memory MCP, structured receipts, usage logs, and audit-ready evidence for agent and CI workflows.

An autonomous memory management system for Claude AI, featuring multi-provider LLM integration and a persistent memory database.

Adaptive error memory & code intelligence MCP server with Hebbian synapse network, cross-project learning, and auto-error detection

Hebbian memory for AI agents — learns file access patterns, builds neural pathways, predicts next tools/files, saves tokens

ByteRover Team Memory is a paid remote MCP endpoint for OpenAI Codex memory MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-ready w

A Neo4j-based MCP server providing persistent memory and contextual assistance for Claude Code.

A persistent memory server for Large Language Models, designed to integrate with the Claude desktop application. It supports tiered memory, semantic search, and automatic memory management.

Persistent memory MCP server for Claude — store decisions, code, and knowledge across sessions.

Provides perfect memory for AI-assisted development by capturing project context snapshots, enabling natural language search, evolution tracking, and code intelligence.

Your AI development companion. An MCP server that gives your AI persistent memory, structured specifications, and adaptive change management — so it builds what you actually want.