x=hub

your toolset

    build deployment
    sign in

    agentic-ledger

    mcpopen · package
    io.github.ShekharBhardwaj/agentic-ledger · v0.15.0
    deploy just this

    Local-first flight recorder for AI agents: sessions, costs, loop runs, and stuck-loop flags.

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    A package that serves HTTP itself; the port comes from its URL template.
    # once, as root:
# as_mcp DIR COMMAND...: runs COMMAND as the mcp user in DIR, its home, sandboxed as the
# units are: a package's install scripts can write to DIR only, as the server later can
as_mcp() {
  local dir="$1"; shift
  systemd-run --quiet --wait --pipe --collect --uid=mcp --gid=mcp \
    -p WorkingDirectory="$dir" -p Environment=HOME="$dir" -p ReadWritePaths="$dir" \
    -p NoNewPrivileges=true -p ProtectSystem=strict -p ProtectHome=true -p PrivateTmp=true \
    -- "$@" </dev/null
}
install -d -m 0750 -o mcp -g mcp /var/lib/mcp/agentic-ledger
# agentic-ledger: its packages, installed whole before its unit starts (no session installs)
systemctl stop mcp-my-agent-agentic-ledger.service 2>/dev/null || true
as_mcp /var/lib/mcp/agentic-ledger uv tool install agentic-ledger==0.15.0

#!/usr/bin/env bash
# agentic-ledger (io.github.ShekharBhardwaj/agentic-ledger), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-agentic-ledger.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec uvx agentic-ledger==0.15.0

[Unit]
Description=MCP server agentic-ledger (toolset my-agent), generated by Hub
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=mcp
Group=mcp
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/agentic-ledger
WorkingDirectory=/var/lib/mcp/agentic-ledger
ExecStart=/opt/mcp/my-agent/bin/agentic-ledger.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/agentic-ledger

[Install]
WantedBy=multi-user.target

    connect to it

    copy what your client needs
    {
  "mcpServers": {
    "agentic-ledger": {
      "command": "CHANGE_ME",
      "args": []
    }
  }
}
    #!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add agentic-ledger -- CHANGE_ME

    {
  "mcpServers": {
    "agentic-ledger": {
      "command": "CHANGE_ME",
      "args": []
    }
  }
}
    {
  "servers": {
    "agentic-ledger": {
      "type": "stdio",
      "command": "CHANGE_ME",
      "args": []
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.ShekharBhardwaj/agentic-ledger
    • not probed yet: tools unpinned, ingest lists them
    • a package that serves HTTP itself: pick a self-hosted target, not 'local'

    tools

    Probe result: faileddocker: the container exited: GROUND (containers, debugging) — same as python -m agenticledger.proxy. options: -h, --help show this help message and exit Downloading uvloop (4.3MiB) Downloading pydantic-core (2.1MiB) Downloaded pydantic-core Downloaded uvloop Installed 26 packages in 41ms; baremetal: the container exited: GROUND (containers, debugging) — same as python -m agenticledger.proxy. options: -h, --help show this help message and exit Downloading uvloop (4.3MiB) Downloading pydantic-co…

    runs · 1

    the latest tests of this entry by the hub and its workers, newest first
    dateworkermethodstatussandboxreason
    2026-10-16 17:34 local-mac-vm docker failed gvisor docker: the container exited: GROUND (containers, debugging) — same as python -m agenticledger.proxy. options: -h, --help show this help message and exit Downlo…