Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CLI_BRIDGE_LEANNoIf set to '1', exposes a curated ~12-tool surface instead of the full set.
APPLE_FM_SERVE_URLNoURL for Apple Foundation Model server (optional, enables Apple PCC lane).
OPENROUTER_API_KEYNoAPI key for the optional OpenRouter lane (hidden until set).
CLI_BRIDGE_HIDE_HOSTNoIf set to '1', the host's own lane is kept out of fan-out operations.
CLI_BRIDGE_MAX_DEPTHNoMaximum delegate re-entry depth (default: 1).
CLI_BRIDGE_LANES_FILENoPath to a custom lanes JSON file to extend or override built-in lanes.
CLI_BRIDGE_DEFAULT_CWDNoDefault working directory for delegates when the host provides no workspace root.
CLI_BRIDGE_TRACE_FOOTERNoSet to 'off' to disable trace footers in responses.
CLI_BRIDGE_DAILY_CREDIT_CAPNoHard daily credit cap enforced at spawn.
CLI_BRIDGE_VERIFY_PLAN_READONLYNoIf set to '1', any read-only delegated plan that writes to the git workspace gets flagged.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
doctorA

Health check: which CLIs are installed, which is the host, paid lanes, defaults, current cost profile. Pass deep=true to also probe each lane with a tiny live call (checks auth/quota — uses a bit of free quota; skips paid lanes).

setupA

Show the cost-profile choice (saver/balanced/max) to walk the user through configuring how cli-bridge spends paid credits/quota. Call this on first use if the profile isn't set, ASK the user, then tell them how to set it.

usage_reportA

Local usage stats (this machine only): total runs, per-lane counts/success/avg latency, ESTIMATED tokens (chars/4) and credits (if CLI_BRIDGE__CREDITS_PER_1K is set), and recent calls. All token/credit figures are estimates, never exact.

usage_budgetA

Per-lane runs since UTC midnight vs an optional CLI_BRIDGE__DAILY_LIMIT (ENFORCED at spawn once reached), plus estimated tokens/credits spent today. Estimates only.

lane_statsA

Per-lane health: total runs, failures, consecutive failures/timeouts, and any active cooldown (a lane in cooldown is skipped by ask_all until it clears).

reset_lane_stateA

Clear a lane's cooldown + failure counters (e.g. after you re-logged in or your quota reset). Pass the lane key, e.g. 'gemini'.

Prompts

Interactive templates invoked by user choice

NameDescription
review_diffMulti-model code review of your current git diff.
security_reviewOWASP-aware multi-model security review of your git diff.
debateDebate a question across several models, then a judge concludes.
cost_setupConfigure how cli-bridge spends paid credits/quota (cost profile).
premortemStress-test a plan across models before building it.
test_planDerive a prioritized test plan from your git diff across models.
apilookupLook up a library/API in CURRENT docs via a web-aware lane (beats a stale training cutoff).

Resources

Contextual data attached and managed by the client

NameDescription
Effective configProfile, guard, terse, and per-lane cost/model.
Lane healthPer-lane runs/failures/cooldown (JSON).
Usage summaryEstimated tokens/credits by lane (JSON).
review_diff schemaJSON schema of the structured review result.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JoaoBerne/cli-bridge-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server