Lets agents query their own usage ledger captured by the Agentic Ledger proxy: sessions with full call traces, costs, loop runs, and stuck-loop flags. Tools include list_sessions, get_session, search, list_runs, get_run_status, and explain.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.AGENTLEDGER_API_KEY— If is set, pass it as a header:AGENTLEDGER_URLAGENTLEDGER_DSN— Postgres? Install the extra and set :AGENTLEDGER_OTEL_ENDPOINT— OpenTelemetry? Install the extra and set :AGENTLEDGER_OTEL_HEADERS— _(none)_ Comma-separated key=value auth headers, e.g. x-honeycomb-team=abc123.AGENTLEDGER_OTEL_SERVICE_NAME— agentledger Value of service.name reported to the collector.AGENTLEDGER_UPSTREAM_URL— e =https://api.openai.com \AGENTLEDGER_HOST— No 0.0.0.0 Host to bind to. Use 127.0.0.1 to restrict to localhost only.AGENTLEDGER_PORT— No 8000 Port to run on.AGENTLEDGER_BUDGET_ACTION— block What happens when a budget is exceeded: block returns HTTP 429 (call never reaches the LLM), warn lets the call through and fires a webhook alert, both blocks and fires the webhook.AGENTLEDGER_RATE_LIMIT_RPM— _(none)_ Max requests per minute globally.AGENTLEDGER_RATE_LIMIT_SESSION_RPM— _(none)_ Max requests per minute per session_id.AGENTLEDGER_RATE_LIMIT_AGENT_RPM— _(none)_ Max requests per minute per agent_name.AGENTLEDGER_RATE_LIMIT_USER_RPM— _(none)_ Max requests per minute per user_id.AGENTLEDGER_ALERT_WEBHOOK_URL— _(none)_ URL to POST alert payloads to. Required for any alerts to fire.AGENTLEDGER_ASYNC_CAPTUREAGENTLEDGER_CAPTURE_QUEUE_MAX— No 10000 Max captures buffered in async mode before load is shed (drops are counted in /metrics).AGENTLEDGER_CAPTURE_LEVEL— No full full stores everything; metadata stores only metrics/metadata (model, tokens, cost, latency, agent, status) and drops prompts, responses, and tools.AGENTLEDGER_REDACTAGENTLEDGER_REDACT_PATTERNS— No _(none)_ Extra redaction regexes as JSON: {"label": "regex", ...} or ["regex", ...].AGENTLEDGER_AUDIT_LOG— No on Record an audit trail of who viewed/exported/deleted what plus token/erasure actions. Set 0 to disable.AGENTLEDGER_LOOP_ACTION— warn warn records loop_flags and fires a loop_flag webhook alert; block additionally returns HTTP 429 (loop_detected) for a session that tripped a guard; off disables inference.AGENTLEDGER_LOOP_MAX_STEPS— _(none)_ Flag (and in block mode, stop) threads that exceed this many ReAct steps.AGENTLEDGER_LOOP_REPEAT_THRESHOLD— 3 Consecutive identical tool calls (same tool, same arguments) before a thread is flagged stuck.AGENTLEDGER_LOOP_RUN_GAP_SECONDS— 900 Max gap between fresh-context spawns (same system prompt) that still count as iterations of one run.AGENTLEDGER_COMPLETION_PROMISE— "ALL TASKS COMPLETE" \AGENTLEDGER_INGEST_KEY— No _(none)_ When set, the proxy forwards a request only if it carries a matching x-agentledger-ingest-key header — closing the open relay. Off by default; a loud startup warning fires when unset.AGENTLEDGER_EXTRA_PATHSAGENTLEDGER_EXPORT_HMAC_KEY— No _(none)_ When set, compliance exports carry a tamper-evident keyed hmac-sha256 integrity tag instead of a plain sha256 checksum.AGENTLEDGER_PRICING— _(none)_ Inline JSON map of model → [input_per_million, output_per_million] USD. E.g. '{"gpt-4o": [2.50, 10.00], "my-model": [1.00, 2.00]}'.AGENTLEDGER_PRICING_FILE— _(none)_ Path to a JSON file with the same format. Applied after AGENTLEDGER_PRICING.[](https://m8ven.ai/mcp/shekharbhardwaj-agenticledger-1rgk3z)