A side-by-side look at the Claude Code Bridge and Preflight MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Claude Code Bridge for coding agents work as a local process; choose Preflight for coding agents as a local process. You can also run both side by side in one mcpServers block.
bridge_send, bridge_receive, bridge_wait.preflight_check, scope_work, clarify_intent.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Coding Agents | Coding Agents |
| Quality signal | 55/100 · Good | 56/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 14 | 13 |
| Directory activity | 0 views 0 installs 0 upvotes | 5 views 0 installs 0 upvotes |
| Tools | 13 | 24 |
| Full listing | View Claude Code Bridge | View Preflight |
bridge_sendSend legacy text or a protocol-v1 message; supports idempotent retriesbridge_receiveRead a bounded page using a message cursor or durable consumer cursorbridge_waitWait up to 55 seconds for new messages without rapid pollingbridge_ackMonotonically advance a consumer's channel-scoped cursorbridge_channelsList active channels and countsbridge_pingCheck bridge health and capabilitiesbridge_statusSummarize recent activity across channelsbridge_clearDelete every message (and task) in one channelbridge_enqueueAdd a task to a channel's work queue (exclusive; claimed once)bridge_claimAtomically claim the next task with a lease; long-poll with `wait_secondsbridge_completeMark a claimed task done, fenced by its `lease_tokenbridge_failFail a claimed task — requeue with backoff, or dead-letterpreflight_checkThe main entry point.** Triages your prompt (trivial → multi-step), chains the right checks automatically, matches against known correction patterns. Accepts `force_level` override: `skip`, `light`, `full`.scope_workCreates structured execution plans before coding startsclarify_intentGathers project context (git state, workspace docs, ambiguity signals) to disambiguate vague promptsenrich_agent_taskEnriches sub-agent tasks with file paths, patterns, and cross-service contextsharpen_followupResolves "fix it" / "do the others" to actual file targetstoken_auditDetects waste patterns, grades your session A–Fsequence_tasksOrders tasks by dependency, locality, and riskcheckpointSave game before compaction — commits + resumption notescheck_session_healthMonitors uncommitted files, time since commit, turn countlog_correctionTracks corrections and identifies recurring error patternscheck_patternsChecks prompts against learned correction patterns — warns about known pitfallssession_handoffGenerates handoff briefs for new sessionsPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"claude-code-bridge": {
"command": "uvx",
"args": [
"claude-code-bridge"
]
}
}
}
{
"mcpServers": {
"preflight-dev-preflight": {
"command": "npx",
"args": [
"-y",
"preflight-dev-serve"
]
}
}
}