Data Sources Beginner

GitHub MCP Integration

2 min read Updated May 19, 2026
Repositories, pull requests, issues, commits, and code search from GitHub, for engineering velocity and review-cycle reporting.

GitHub hosts code, pull requests, and issues for nearly every engineering team. Connecting GitHub to clariBI puts repository activity into your AI analyses for engineering velocity and code review insights.

Why connect GitHub

Engineering metrics often span Jira, Linear, GitHub, and CI tools. Pulling them together usually requires custom scripts.

With GitHub connected, you can ask "How many PRs shipped this sprint?", "Find PRs without reviews older than 3 days", or "Compare review time across teams" without leaving clariBI.

How the connection works

clariBI talks to GitHub through its hosted MCP server at https://api.githubcopilot.com/mcp. Authentication uses an OAuth flow against an OAuth app you register in the vendor's developer console. Tokens stay encrypted server-side and never leave clariBI in clear form.

sequenceDiagram
    actor U as You
    participant C as clariBI
    participant V as GitHub
    U->>C: Click Authorize with GitHub
    C->>V: Open OAuth authorization
    V-->>U: Grant read access?
    U->>V: Approve
    V-->>C: Authorization code
    C->>V: Exchange code for tokens
    V-->>C: Access + refresh tokens
    C->>C: Encrypt and store credentials
    C-->>U: Connection ready

Available tools

clariBI exposes the read-only GitHub tools that the vendor's MCP server publishes at connection time. Write operations (create, update, delete, send, refund) are filtered out by a name-pattern blocklist before any tool reaches the analysis engine, so connecting GitHub cannot modify data on the vendor side.

The exact tool inventory depends on the GitHub features your account has access to. After connecting, try a few natural-language questions to see what GitHub data clariBI can pull.

Data flow during analysis

When you ask a question that maps to GitHub, the AI engine routes to the right tool, reads the result, and pairs the answer with a chart you can pin to a dashboard.

sequenceDiagram
    actor U as You
    participant C as clariBI
    participant AI as AI engine
    participant V as GitHub
    U->>C: Ask a question about repository and PR data
    C->>AI: Plan the analysis
    AI->>V: Call the right tool
    V-->>AI: Tool result
    AI->>AI: Summarize and chart
    C-->>U: Answer plus visual

Setting up the connection

  1. Open Data Sources in the clariBI sidebar.
  2. Click Add data source.
  3. Open the MCP Servers tab.
  4. Click the GitHub card.
  5. Click Authorize with GitHub.
  6. Sign in to GitHub in the popup window and grant the requested read scopes.
  7. Back in clariBI, give your data source a name.
  8. Click Finish.

Permissions and data access

clariBI requests repo, read:org, and read:user scopes. No code can be committed or pushed, no PRs merged, and no issues modified. Disconnect from GitHub account settings or from clariBI Settings.

Troubleshooting

ErrorCauseFix
"Private repo not visible"Your account does not have access to a referenced private repo.Confirm repo visibility in GitHub, or use a public repo as a test.

Related articles

Related Articles

Data Sources Intermediate

Morningstar MCP Integration

Investment research, fund data, ratings, fair-value estimates, and 200,000+ global securities from …

5 min read
Data Sources Intermediate

Keboola MCP Integration

Data pipelines, transformations, tables, and project metadata from the Keboola data-platform — for …

5 min read
Data Sources Intermediate

Logfire (EU) MCP Integration

OpenTelemetry traces, metrics, and logs from Pydantic Logfire (EU region) — for EU-resident custome…

5 min read

Still Need Help?

Can't find what you're looking for? Our support team is here to help you succeed with clariBI.