GitHub + Linear Dev Workflows
Provides tools for interacting with GitHub repositories, issues, pull requests, releases, security alerts, and CI workflows; enables workflows like linking PRs to Linear issues, creating issues from failing CI, and tracking stale reviews.
Provides OAuth-based access to Google services; supports workflows involving Google Docs, Google Calendar, and Google Sheets.
Provides tools for reading and creating Google Calendar events; used for on-call handoffs, postmortem review dates, and scheduling.
Provides tools for creating and reading Google Docs; used for incident postmortems, design notes, and repo onboarding documentation.
Provides tools for reading and writing Google Sheets; used for flaky test ledgers, CI spend reports, and TODO/FIXME debt registers.
Provides tools for interacting with Linear issues, teams, projects, and cycles; enables creating and updating issues, linking work items, and syncing GitHub, CI, Slack, and postmortem actions into Linear.
Provides tools for creating and updating Notion pages and databases; enables changelogs, dependency records, and engineering wiki content from GitHub docs.
Provides tools for sending messages, posting alerts, reading threads, and managing Slack channels; enables notifications, standup digests, bug reports, deploy approvals, and incident timelines.
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., "@GitHub + Linear Dev WorkflowsTurn the failing CI on main into a Linear bug with the log excerpt and notify Slack"
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.
GitHub + Linear Dev Workflows
CI failures, PRs and security alerts become Linear issues and Slack posts, evidence attached.
An MCP server with 25 workflows across GitHub, Linear, Slack, Notion, Google Docs, Google Calendar, Firecrawl, Google Sheets and Tavily. Each workflow is a prompt your agent runs as a slash command, over the 59 tools it needs and no others.
uv tool install https://github.com/r28ai/github-linear-mcp/releases/download/v0.1.0/github_linear_mcp-0.1.0-py3-none-any.whl
claude mcp add dev -- github-linear-mcpIt installs with uv from this repository's release, with no git and nothing to build; nothing but Charter and the libraries it uses comes from PyPI. To update, run the install line from the latest release. If a desktop app cannot find github-linear-mcp, give it the full path from which github-linear-mcp (where github-linear-mcp on Windows).
Then ask your agent to connect your apps, or run /mcp__dev__setup.
Connect your apps
Ask the agent to connect one ("connect Linear"). It tells you where to get that app's key and the command that stores it, and the next call works, with no restart. The agent never asks for a key in the chat.
Or connect everything this server uses from a terminal:
github-linear-mcp login # each app in turn
github-linear-mcp login github # just one
github-linear-mcp status # what is connectedTokens and keys go to your operating system's keychain (macOS Keychain, Windows Credential Manager, the Secret Service on Linux), and are checked with one read-only call to the app's own API before they are kept. Every key, token and OAuth client is yours: we register no app with any of these services, and nothing passes through a server of ours, because there isn't one.
App | How it connects | Or set |
GitHub | Your own key (get one), entered once. |
|
Linear | Your own key (get one), entered once. |
|
Slack | Your own key (get one), entered once. A bot token from your own Slack app, which the guide sets up in about three minutes. |
|
Notion | Your own key (get one), entered once. Then share the pages it should see with the integration. |
|
Browser sign-in, over your own OAuth client (make one). |
| |
Firecrawl | Your own key (get one), entered once. |
|
Tavily | Your own key (get one), entered once. |
|
A variable set in your client's config always wins over the keychain.
Related MCP server: MCP Setup Server
Workflows
Workflow | What you get | Apps |
Failing CI → bug with the log excerpt | A red main branch becomes an owned issue with the failing step quoted, not a channel ping. | GitHub, Linear, Slack |
Link every PR to its Linear issue | No orphan PRs, so cycle reports and changelogs stop missing work. | GitHub, Linear |
Security alerts → Linear | Critical alerts get owners and due dates in the tracker the team actually reads. | GitHub, Linear |
Leaked secret → page a human | An exposed key is an urgent issue and a loud message within minutes. | GitHub, Linear, Slack |
Release → changelog page and announcement | Every release has a readable changelog without a release manager writing it. | GitHub, Notion, Slack |
Standup digest per person | Yesterday's PRs and today's issues in a DM, so standup is about blockers. | GitHub, Linear, Slack |
Stale review nudger | PRs waiting more than a day get a polite DM to the right reviewer. | GitHub, Slack |
Linear issue → branch and draft PR | Starting work on an issue sets up the branch, the PR and the link. | Linear, GitHub |
Incident timeline → postmortem draft | The timeline is assembled from what happened, and action items are tracked from minute one. | Slack, GitHub, Google Docs, Linear |
Postmortem actions tracked to done | Follow-ups from the postmortem become linked issues with a review date. | Google Docs, Linear, Google Calendar |
Slack bug report → Linear | The thread becomes an issue with repro steps, and the thread gets the link. | Slack, Linear |
GitHub issues mirrored into Linear | Open-source reports enter the internal tracker without double triage. | GitHub, Linear |
Vendor deprecation → affected files | A deprecation notice arrives already mapped to the code that uses the old API. | Firecrawl, GitHub, Linear |
On-call handoff | The next on-call starts with open urgents and unread alerts in one message. | Google Calendar, Linear, GitHub, Slack |
Deploy approval from Slack | Production deploys gated on an explicit 'approve' in a thread, with the reviewer on record. | GitHub, Slack |
Flaky test ledger | Tests that fail and pass on retry get counted until one crosses the line and gets an issue. | GitHub, Google Sheets, Linear |
CI spend report | Which workflows burn the minutes, weekly, before the bill does it. | GitHub, Google Sheets, Slack |
PR → design note in Docs | A large PR gets a readable explanation for reviewers outside the team. | GitHub, Google Docs |
Dependency choice with real repo health | Library choices recorded with stars, activity and bus factor, not vibes. | Tavily, GitHub, Notion |
Slack debate → ADR in the repo | The decision and its reasons get committed next to the code they govern. | Slack, GitHub, Linear |
Repo onboarding doc | A new engineer gets a map of an unfamiliar repo and who to ask. | GitHub, Google Docs |
Stale PR cleanup | Month-old PRs are closed with a note and the author is told, so the queue means something. | GitHub, Slack |
TODO/FIXME debt register | Debt hiding in comments becomes a list someone can prioritise. | GitHub, Linear, Google Sheets |
Repo docs → engineering wiki | The wiki mirrors docs/ in the repo instead of drifting from it. | GitHub, Notion, Slack |
Release credits for contributors | Every release thanks the people who made it, by name. | GitHub, Slack |
Every prompt takes one optional argument, details: the repo, team, channel, customer or date range you mean, so the agent does not have to ask. In Claude Code, put it in quotes, or only its first word arrives:
/mcp__dev__failing_ci_to_bug_with_the_log_excerpt "repo acme/api, Linear team ENG, post in #eng-alerts"Reads run without asking. Before anything that creates, sends, changes or deletes, the prompt tells the agent to show you the call and wait.
17 of the 25 workflows need no Google or Granola credential.
Other clients
Claude Desktop: install uv if you have not, since Claude Desktop starts the server with it, then open the .mcpb from the latest release. Claude asks for any keys in its own settings and keeps them in your keychain. The first start takes a few seconds longer, while uv installs it.
VS Code (.vscode/mcp.json): VS Code asks for each key the first time the server starts and stores it securely. Leave out any you stored with login.
{
"inputs": [
{
"type": "promptString",
"id": "github-token",
"description": "GitHub: Personal access token",
"password": true
},
{
"type": "promptString",
"id": "linear-api-key",
"description": "Linear: Personal API key",
"password": true
},
{
"type": "promptString",
"id": "slack-bot-token",
"description": "Slack: Bot token (xoxb-\u2026)",
"password": true
},
{
"type": "promptString",
"id": "notion-api-key",
"description": "Notion: Integration secret (ntn_\u2026)",
"password": true
},
{
"type": "promptString",
"id": "google-client-secret",
"description": "Google: OAuth client secret",
"password": true
},
{
"type": "promptString",
"id": "firecrawl-api-key",
"description": "Firecrawl: API key",
"password": true
},
{
"type": "promptString",
"id": "tavily-api-key",
"description": "Tavily: API key",
"password": true
}
],
"servers": {
"dev": {
"type": "stdio",
"command": "github-linear-mcp",
"env": {
"GITHUB_TOKEN": "${input:github-token}",
"LINEAR_API_KEY": "${input:linear-api-key}",
"SLACK_BOT_TOKEN": "${input:slack-bot-token}",
"NOTION_API_KEY": "${input:notion-api-key}",
"GOOGLE_CLIENT_SECRET": "${input:google-client-secret}",
"FIRECRAWL_API_KEY": "${input:firecrawl-api-key}",
"TAVILY_API_KEY": "${input:tavily-api-key}",
"GOOGLE_CLIENT_ID": ""
}
}
}
}Cursor (.cursor/mcp.json) starts it the same way:
{
"mcpServers": {
"dev": {
"command": "github-linear-mcp"
}
}
}Codex (~/.codex/config.toml) starts a turn without waiting for a server unless it is required, and then the agent has none of its tools. required = true makes the session wait for it, and startup_readiness = "catalog" waits for its tool list rather than just its connection:
[mcp_servers.dev]
command = "github-linear-mcp"
required = true
startup_readiness = "catalog"
startup_timeout_sec = 30Name the server dev. A host builds each tool's name from that key, and a longer one can push a tool past the 64 characters a function name allows.
Built with Charter
Every tool here is a Charter declaration: a Pydantic schema saying where each field goes on the wire. Charter's runtime builds the request, attaches and refreshes the credential, and trims the response before the model reads it. It runs in your process, with no proxy and no telemetry.
The 59 tool schemas come to 57,249 tokens.
The same tools work in your own agent, without MCP:
from charter.adapters.openai import to_openai_tools
from charter_packs_mcp import FAMILIES
tools = FAMILIES["engineering"].tools()
definitions = to_openai_tools(tools) # or charter.adapters.langchainNeed an API that isn't here? Write a pack: your coding agent writes the declarations, and Charter's conformance suite checks them.
GitHub:
github_actions_list_workflow_runs,github_actions_list_jobs_for_run,github_actions_download_job_logs,github_pulls_list,github_dependabot_list_alerts,github_code_scanning_list_alerts,github_secret_scanning_list_alerts,github_releases_get_latest,github_repos_compare_commits,github_search_issues,github_pulls_list_requested_reviewers,github_git_refs_get,github_git_refs_create,github_pulls_create,github_repos_list_commits,github_issues_list_for_repo,github_issues_create_comment,github_search_code,github_notifications_list,github_actions_list_pending_deployments,github_actions_review_pending_deployments,github_actions_list_runs_for_workflow,github_checks_list_annotations,github_actions_get_run_usage,github_pulls_get,github_pulls_list_files,github_pulls_get_diff,github_search_repositories,github_repos_get,github_repos_list_contributors,github_repos_create_or_update_file,github_repos_get_readme,github_repos_list_languages,github_pulls_update,github_repos_get_content,github_releases_updateLinear:
linear_issue_create,linear_attachments_for_url,linear_search_issues,linear_attachment_create,linear_issues_list,linear_issue_get,linear_issue_relation_createSlack:
slack_chat_post_message,slack_conversations_open,slack_users_list,slack_conversations_history,slack_conversations_repliesNotion:
notion_pages_create,notion_pages_update_markdownGoogle Docs:
gdocs_documents_create,gdocs_documents_getGoogle Calendar:
gcalendar_events_insert,gcalendar_events_listFirecrawl:
firecrawl_monitor_create,firecrawl_monitor_checks_listGoogle Sheets:
gsheets_spreadsheets_values_append,gsheets_spreadsheets_values_updateTavily:
tavily_search
License
Apache 2.0.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Open-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server that equips AI agents with dev workflow tools including GitHub project management, conventional commits, visual regression testing, Jira/Confluence integration, and a persistent memory knowledge graph.11 npmMIT
- FlicenseNot gradedqualityDmaintenanceA modular MCP server exposing tools for integrating with services like GitHub, Redash, Jenkins, Figma, Jira, Confluence, Teams, Datadog, PagerDuty, Slack, and Presto, enabling users to manage these platforms through natural language via an MCP client.-
- FlicenseAqualityCmaintenanceMCP server that enables AI assistants to run multi-step agent pipelines (e.g., Issue Analyst → Code Writer → Test Runner → PR Opener) from conversations, with support for Devin, shell, Python, and HTTP agents.7-
- FlicenseNot gradedqualityCmaintenanceEnterprise MCP server providing a suite of tools including file, database, GitHub, Slack, calendar, email, vector search, and Python execution, with safe defaults and OpenAI integration for automatic tool selection.-