COS-MCP
Integrates with GitHub to enrich organizational knowledge graph with repository metadata, contributor analysis, commit/PR history, and ownership risk analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@COS-MCP analyze knowledge risk for the frontend team"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
COS-MCP
Continuity OS — The Operating System for Organizational Continuity
COS-MCP is an MCP (Model Context Protocol) server that provides AI-powered organizational continuity planning. It maintains a knowledge graph of employees, systems, projects, and relationships, and exposes tools, resources, and prompts for knowledge graph visualization, risk analysis, employee transition planning, and organizational knowledge base queries.
Built with NitroStack — @nitrostack/core for the MCP server and @nitrostack/widgets for UI widgets.
Features
Knowledge Graph — Complete graph of employees, systems, projects, decisions, customers, and their relationships
Risk Analysis — Bus factor calculation, knowledge concentration detection, sole-owner identification
Transition Planning — Composed transition plans, successor scoring, onboarding path generation
GitHub Integration — Repository metadata, contributor analysis, commit/PR history, ownership risk
Organizational Knowledge Base — Decision records (ADRs), meeting summaries, documentation snippets with natural language querying
NitroStack Widgets — Pre-built dashboards and visualizations (Health Dashboard, Ownership Graph, GitHub insights)
MCP Prompts — Structured AI prompts for knowledge transfer summaries, transition reports, health checks, customer handovers
Related MCP server: portuni
Architecture
cos-mcp/
├── src/
│ ├── index.ts # Entry point — boots MCP server
│ ├── app.module.ts # Root @McpApp + @Module
│ ├── models/index.ts # Zod schemas + TypeScript types
│ ├── services/
│ │ ├── mock-data.service.ts # In-memory data store (employees, projects, systems, graph)
│ │ └── github.service.ts # GitHub REST API client with caching
│ ├── modules/
│ │ ├── knowledge-graph/ # Org resources, graph tools, knowledge base, prompts
│ │ │ ├── knowledge-graph.module.ts
│ │ │ ├── knowledge-graph.tools.ts # build_ownership_graph, find_domain_experts, etc.
│ │ │ ├── knowledge-graph.resources.ts # org://employees, org://teams, org://systems, etc.
│ │ │ ├── knowledge-graph.prompts.ts # knowledge_transfer_summary, transition_report, etc.
│ │ │ └── knowledge-base.ts # Static ADRs, meeting summaries, docs
│ │ ├── risk/ # Risk analysis tools
│ │ │ ├── risk.module.ts
│ │ │ └── risk.tools.ts # analyze_knowledge_risk, calculate_bus_factor
│ │ ├── transition/ # Transition planning tools
│ │ │ ├── transition.module.ts
│ │ │ └── transition.tools.ts # generate_transition_plan, recommend_successor, etc.
│ │ └── github/ # GitHub integration
│ │ ├── github.module.ts
│ │ ├── github.tools.ts # sync_github_repository, analyze_repository_ownership, etc.
│ │ └── github.resources.ts # github://repo, github://contributors, github://commits
│ └── widgets/ # NitroStack widget pages (Next.js static export)
│ ├── app/ # Page components
│ ├── widget-manifest.json # Widget registry
│ ├── next.config.mjs
│ └── package.json
└── package.jsonModule Structure
Module | Path | Description |
App |
| Root module, imports all feature modules |
KnowledgeGraph |
| Core module — resources, tools, prompts, knowledge base |
Risk |
| Bus factor and knowledge concentration analysis |
Transition |
| Transition plans, successor recommendations, onboarding |
GitHub |
| GitHub REST API integration |
Installation
# Clone the repository
git clone https://github.com/your-org/cos-mcp.git
cd cos-mcp
# Install dependencies
npm install
# (Optional) Install widget dependencies
cd src/widgets && npm install && cd ../..Environment Variables
Copy .env.example to .env:
cp .env.example .envVariable | Required | Default | Description |
| No |
| Environment ( |
| No |
| Port the MCP server listens on |
| No | — | GitHub personal access token (5,000 req/hr vs 60 req/hr unauthenticated) |
Running Locally
# Start the MCP server in dev mode (with hot reload via NitroStudio)
npm run dev
# Or build and run
npm run build
npm startWidgets (optional)
# Dev server for widgets
npm run widgets:dev
# Build widgets for production (static export)
npm run widgets:buildBuild Instructions
# TypeScript compilation
npm run build
# Build output goes to ./dist/
# Entry point: ./dist/index.jsGitHub Integration
COS-MCP integrates with the GitHub REST API to enrich the organizational knowledge graph with live repository data.
GitHub Tools
Tool | Description |
| Fetch repository metadata, contributors, commits, PRs, and languages |
| Calculate bus factor, contribution percentages, ownership risk |
| Merge GitHub commit/PR/ownership data into an employee profile |
GitHub Resources
URI | Description |
| Repository metadata, contributors, commits, PRs, languages |
| Contributor list with commit counts |
| Recent commit history |
Setup
export GITHUB_TOKEN=ghp_your_token_hereDemo Workflow
1. Explore the Organization
GET org://employees
GET org://teams
GET org://teams/Payments
GET org://employees/emp_0012. Build Ownership Graph
Tool: build_ownership_graph
Input: { employeeId: "emp_001" }3. Analyze Knowledge Risk
Tool: analyze_knowledge_risk
Input: { scope: "organization" }4. Find Domain Experts
Tool: find_domain_experts
Input: { domain: "payments" }5. Identify Hidden Dependencies
Tool: identify_hidden_dependencies
Input: { employeeId: "emp_001" }6. Query Organizational Knowledge
Tool: query_organizational_knowledge
Input: { question: "Why did Alice choose Kafka over RabbitMQ?" }7. Recommend Successor
Tool: recommend_successor
Input: { roleId: "Senior Engineer", departingEmployeeId: "emp_001" }8. Generate Transition Plan
Tool: generate_transition_plan
Input: { departingEmployeeId: "emp_001", successorId: "emp_013" }9. Use AI Prompts
Prompt: knowledge_transfer_summary
Arguments: { employeeId: "emp_001", format: "detailed" }
Prompt: role_transition_report
Arguments: { departingId: "emp_001", successorId: "emp_013" }
Prompt: organizational_health_check
Arguments: { scope: "team", teamId: "Payments" }10. Create Onboarding Path
Tool: create_onboarding_path
Input: { newEmployeeId: "emp_013", roleId: "Senior Engineer" }MCP Tools
Tool | Module | Description | Widget |
| KnowledgeGraph | Build a complete ownership sub-graph for an employee |
|
| KnowledgeGraph | Search for domain experts by skills, system ownership, GitHub | — |
| KnowledgeGraph | Surface non-obvious responsibilities and hidden dependencies | — |
| KnowledgeGraph | Natural language query of ADRs, meetings, docs | — |
| Risk | Bus factor, sole owners, undocumented systems per team |
|
| Risk | Bus factor for a specific team | — |
| Transition | Composed transition plan (ownership + risk + successor) | — |
| Transition | Score and rank potential successors | — |
| Transition | Structured learning path for new hires | — |
| GitHub | Fetch repository metadata, contributors, commits, PRs |
|
| GitHub | Bus factor, contribution %, ownership risk |
|
| GitHub | Merge GitHub data into employee profile | — |
MCP Resources
URI | Module | Description |
| KnowledgeGraph | All employees with roles, teams, skills |
| KnowledgeGraph | Employee details with projects, systems, relationships |
| KnowledgeGraph | All teams with member counts, bus factor, health |
| KnowledgeGraph | Team breakdown with members, risk, projects, systems |
| KnowledgeGraph | All systems with ownership, documentation status |
| KnowledgeGraph | All projects with ownership, contributors, systems |
| KnowledgeGraph | Full knowledge graph (nodes + edges) |
| GitHub | Repository metadata, contributors, commits, PRs, languages |
| GitHub | Contributor list with commit counts |
| GitHub | Recent commit history |
MCP Prompts
Prompt | Module | Description |
| KnowledgeGraph | KT summary for departing employee |
| KnowledgeGraph | Complete transition report with risk, readiness, timeline |
| KnowledgeGraph | Org-wide or team health assessment with RAG status |
| KnowledgeGraph | Customer relationship handover document |
Widgets
Widget | Route | Bound Tool |
Organizational Health Dashboard |
|
|
Employee Ownership Graph |
|
|
GitHub Repositories |
|
|
Top Contributors |
|
|
Repository Bus Factor |
|
|
Commit Activity |
|
|
Ownership Percentage |
|
|
Critical Repositories |
|
|
Deployment
Production Build
npm run buildRun with PM2 (recommended)
npm install -g pm2
pm2 start dist/index.js --name cos-mcpDocker (example Dockerfile)
FROM node:22-alpine
WORKDIR /app
COPY package*.json ./
RUN npm ci
COPY dist/ ./dist/
CMD ["npm", "start"]Environment Variables
Ensure these are set in your production environment:
NODE_ENV=production
PORT=3000
GITHUB_TOKEN=ghp_your_tokenExample Usage
# Query all employees
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"resources/read","params":{"uri":"org://employees"},"id":1}'
# Build ownership graph
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"build_ownership_graph","arguments":{"employeeId":"emp_001"}},"id":2}'
# Sync GitHub repository
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"sync_github_repository","arguments":{"owner":"nitrocloudofficial","repo":"nitrostack"}},"id":3}'Organization Data
3 teams: Payments (6 members), Platform (5 members), Growth (3 members)
8 projects: Payment Gateway v3, Platform Migration to EKS, User Onboarding Redesign, Real-Time Fraud Detection, Data Lake Foundation, API Rate Limiter, A/B Testing Platform, PCI DSS Compliance Audit
9 systems: Payment Processor, Ledger Service, API Gateway, Event Bus, User Service, Internal Admin Dashboard, Payment Reconciliation Service, SAP Integration, Vendor X Process
12 decision records (ADR-001 through ADR-012)
5 meeting summaries
8 documentation snippets
License
MIT
Available Tools
12 toolsanalyze_knowledge_riskARead-only
Analyze organizational knowledge risk by calculating bus factor per team. Identifies sole owners of critical systems, undocumented services, and single points of failure. Use this when you need to assess continuity risk, identify knowledge silos, or determine which teams are most vulnerable to employee departure.
Inputs: scope, teamId.
analyze_repository_ownershipARead-only
Analyze a GitHub repository's contributor data to calculate bus factor, knowledge concentration, contribution percentages, and ownership risk. Provides recommendations for reducing single-contributor risk.
Inputs: repo (required), owner (required).
build_ownership_graphARead-only
Build a complete ownership sub-graph for a given employee. Traverses all relationships to surface projects owned or contributed to, systems where they are sole or primary owner, documents and processes they run, people who depend on them, customers they manage, and architectural decisions they made. Use this to visualize an employee's full organizational footprint and identify knowledge concentration risks.
Inputs: employeeId (required).
calculate_bus_factorARead-only
Calculate the bus factor for a specific team. The bus factor is the minimum number of team members whose simultaneous departure would halt critical systems. Use this when evaluating team resilience, planning for personnel changes, or preparing for knowledge transfer.
Inputs: teamId (required).
create_onboarding_pathA
Generate a structured learning path for a new employee based on organizational knowledge. Maps out what systems to learn first (in dependency order), who to meet, what documentation to read, and milestones to achieve each week. Use this to accelerate new hire ramp-up using the organization's knowledge graph.
Inputs: roleId (required), newEmployeeId (required).
enrich_employee_profileA
Enrich an existing employee profile with GitHub activity data. Merges commits, pull requests, last activity, and repository ownership into the employee's organizational profile.
Inputs: repo (required), owner (required), employeeName (required), githubUsername (required).
find_domain_expertsARead-only
Search through employee skills, system ownership, and project involvement to find domain experts. Scores and ranks employees by relevance to a given domain (e.g. "payments", "kubernetes", "react"). Use this when you need to identify who to consult for a specific technical or business domain.
Inputs: domain (required).
generate_transition_planA
Generate a comprehensive transition plan for a departing employee. Analyzes the employee's full ownership graph (systems, projects, processes, decisions, dependents), prioritizes handovers by criticality, and produces a phased timeline with task assignments. Use this when an employee is leaving or changing roles to ensure continuity.
Inputs: departingEmployeeId (required), lastDay, successorId.
query_organizational_knowledgeARead-only
Search the organizational knowledge base for decisions, documentation, meeting outcomes, or technical rationale. Understands natural language questions about why certain technologies were chosen, how systems are designed, what was decided in meetings, and where documentation lives. Use this as the primary tool for answering "why" and "how" questions about the organization's technical history.
Inputs: question (required), context.
recommend_successorARead-only
Score and rank potential successors for a departing employee based on skill overlap, team proximity, existing system knowledge, and current capacity. Use this when you need to identify the best person to backfill or absorb responsibilities from a leaving team member.
Inputs: roleId (required), departingEmployeeId (required).
sync_github_repositoryA
Fetch and sync a GitHub repository's data including metadata, contributors, commits, pull requests, and languages. Stores the data in the knowledge graph for further analysis.
Inputs: repo (required), owner (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Several tools overlap around bus factor and ownership analysis. analyze_repository_ownership, analyze_knowledge_risk, and calculate_bus_factor all deal with bus factor at different scopes (repo, org, team), which could cause misselection. identify_hidden_dependencies and build_ownership_graph also have overlapping purposes in surfacing employee responsibilities, though they differ in focus on hidden vs. comprehensive dependencies.
All tool names follow a consistent verb_noun snake_case pattern (e.g., analyze_repository_ownership, calculate_bus_factor, generate_transition_plan). The verbs are distinct and descriptive, making the naming predictable and easy to navigate.
12 tools is well-scoped for the domain of organizational knowledge, bus factor, and transition planning. Each tool serves a distinct functional need, from data ingestion (sync_github_repository, enrich_employee_profile) to analysis (bus factor, ownership graph) to actionable planning (transition plans, onboarding paths). No tool feels redundant or unnecessary.
The tool surface covers the core workflow of assessing continuity risk and planning transitions: identify risks (bus factor, hidden dependencies), analyze ownership, find experts, generate transition plans and onboarding paths. Minor gaps include lack of a direct tool to edit or remove organizational knowledge entries, but the existing tools provide sufficient coverage for the primary use case.
Maintenance
Related MCP Connectors
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that builds a knowledge graph from code and text documents, enabling Q\&A and implementation planning via tools like graph_create, graph_plan, and graph_query.7MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that provides a shared graph of an organization's projects, processes, areas, and principles, enabling consistent context for tools and AI agents.2Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP server that connects AI agents to a shared organizational knowledge base, allowing them to query company-specific context like pricing, team, and strategy.MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that enables AI agents to search, fetch, and analyze a self-maintaining markdown knowledge base with provenance, drift detection, and canonical definitions.1MIT