LaunchChair MCP server

Read from the package source without running it. The installed server may list more.

• launchchair_claim_next_runwrite action

  Claim next queued Run with Agent job for token/project.

• launchchair_complete_runwrite action

  Complete/fail a claimed run by id. LaunchChair handles configured apply, validation, retry, and remediation decisions after completion.

• launchchair_continue_project

  Continue a LaunchChair project loop: inspect project state, queue the next agent-actionable step, execute it with the configured runner, complete it, apply/validate/remediate through LaunchChair, and return phase synthesis links when phases finish.

• launchchair_create_projectwrite action

  Create a new LaunchChair Product project in the token workspace, optionally save the first Idea Snapshot, and optionally start the project loop. Requires a workspace-scoped token with projects.write.

• launchchair_get_scorecards

  Read the Product or Feature validation scorecards for a project, including recommended thresholds and direction-option scores kept separate. Use this whenever the user asks about validation scores or wants to compare/rerun ideas until the scorecards are strong.

• launchchair_heartbeatwrite action

  Send heartbeat and update connected agent metadata.

• launchchair_list_projects

  List LaunchChair projects visible to the current Agent API token. Use this to resolve a user-provided project name like LeafLore when LAUNCHCHAIR_PROJECT_ID is not configured.

• launchchair_run_oncewrite action

  Claim next queued run, execute local runner, then complete run.

• launchchair_select_choice

  Select or change a generated LaunchChair user-choice option, such as wedge, pricing, or feature direction. Use this instead of generic SPEC_UPDATE for user-choice buckets.

• launchchair_status

  Read LaunchChair Agent API catalog and scopes.

• Code scan10 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenanceno repository listed3/15
• Maintainer identityverified namespace with website, no repo4/10

Safety score

58/100

higher than 13% of 2,174 E-commerce servers

Tools

10

the typical E-commerce server has 6

Tools that change things

50%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

45

more than 42% of 411 E-commerce servers with a package

LaunchChair: common questions

Is LaunchChair MCP server safe?

With care: it is graded C, so read the findings first (58/100). Read the LaunchChair safety report

How do I install LaunchChair?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does LaunchChair need an API key?

Yes. The registry entry asks for LAUNCHCHAIR_AGENT_TOKEN.

Is LaunchChair maintained?

The latest release is v0.4.10.

What can I use instead of LaunchChair?

Servers from other publishers that do the same job: PostHog MCP Server, Loki Mode MCP server and New-Term Radar MCP server.

How does LaunchChair compare with other E-commerce MCP servers?

safety score 58/100 (higher than 13% of 2,174 E-commerce servers); tools 10 (the typical E-commerce server has 6); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.