Official description7 sourcesMCP servers8d ago
ejcho623/agent-breadcrumbs
๐ โ๏ธ ๐ - Unified work logging and observability across AI agents, with config-first schemas and pluggableโฆ
View on GitHub โDirect link ยท no redirect page
Config template (adjust for your client)
claude mcp add agent-breadcrumbs -- npx -y agent-breadcrumbs
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
- Star count
- 4 โ ยท ejcho623/agent-breadcrumbs ยท read from the GitHub search API ยท (checked 2026-10-16 20:00:20)
- Source
- collected from the punkpeye/awesome-mcp-servers list ยท type: MCP server
- Harvest history
- first seen 2026-10-09 ยท last seen 2026-10-16 ยท seen 32ร ยท listed by 7 sources
- Score
- score 703 ยท 4 โ ยท 7 sources ยท mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP ๆๅก. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
ejcho623/agent-breadcrumbs๏ผfirst catalogued 2026-10-09๏ผlast seen 2026-10-16ใThere is no official certification or quality rating here โ we record sources and dates only.Third-party quality signals
Agent Breadcrumbs ๐
ไปฅไธๆๅฝ่ช่ฏฅไปๅบ็ README๏ผ็ๆฎต๏ผ ยท ๅจ GitHub ่ฏปๅฎๆด README โ
Lightweight logging & observability for agent work across clients (Codex, Claude, Cursor, ChatGPT, OpenClaw, and others).
https://github.com/user-attachments/assets/3eac31a8-107c-4a82-a14c-dcfa500dd1a9
What You Get
- One MCP tool (log_work) that aggregates work done across different agents for single or multiple users.
- Define your own logging structure with custom schemas (or use built-in profiles) once, and the MCP schema
will guide clients to log with correct payloads.
- This lets teams standardize logging once, then route data wherever they need it.
- Multiple options for output sinks:
- local JSONL
- webhook
- Postgres
- Starter schema profiles for common use cases:
- agent insights
- delivery tracking
- audit trail
- knowledge capture
- Simple dashboard app to view logged work.
Repository Layout
- MCP server package (published): packages/mcp
- Dashboard app (repo-local, not published): apps/dashboard
Quick Start (MCP)
Install and run with defaults:
Use with an explicit config file:
Codex config example (~/.codex/config.toml):
--config is optional. If omitted, server defaults are used:
Claude Desktop (claude_desktop_config.json):
OpenClaw:
After you install the MCP server make sure to use mcporter so the server can be called through the CLI.
Then add a system prompt to the channel you're using.
For cron-driven workflows, instruct agents to call log_work on each scheduled run
for regular time-based logging.
General example global instruction/system prompt for clients:
For full MCP server setup, config, and sink details, see packages/mcp/README.md.
Quick Start (Repo)
Run MCP server locally with a sample config:
Run dashboard locally:
MCP Config Model
Top-level config file is JSON and supports:
- schema for fully custom log_record properties, or
- schema_profile for built-in profile files in packages/mcp/examples/schema_profiles
- user_name for server-side user identity injection into persisted records
- sink for destination settings (jsonl, webhook, postgres)
Do not set both schema and schema_profile together.
Default behavior when omitted:
- schema: built-in default (agent_id, timestamp, work_summary, additional)
- sink: jsonl
- output file: ~/.agent-breadcrumbs/logs.jsonl
https://github.com/user-attachments/assets/3eac31a8-107c-4a82-a14c-dcfa500dd1a9
What You Get
- One MCP tool (log_work) that aggregates work done across different agents for single or multiple users.
- Define your own logging structure with custom schemas (or use built-in profiles) once, and the MCP schema
will guide clients to log with correct payloads.
- This lets teams standardize logging once, then route data wherever they need it.
- Multiple options for output sinks:
- local JSONL
- webhook
- Postgres
- Starter schema profiles for common use cases:
- agent insights
- delivery tracking
- audit trail
- knowledge capture
- Simple dashboard app to view logged work.
Repository Layout
- MCP server package (published): packages/mcp
- Dashboard app (repo-local, not published): apps/dashboard
Quick Start (MCP)
Install and run with defaults:
Use with an explicit config file:
Codex config example (~/.codex/config.toml):
--config is optional. If omitted, server defaults are used:
Claude Desktop (claude_desktop_config.json):
OpenClaw:
After you install the MCP server make sure to use mcporter so the server can be called through the CLI.
Then add a system prompt to the channel you're using.
For cron-driven workflows, instruct agents to call log_work on each scheduled run
for regular time-based logging.
General example global instruction/system prompt for clients:
For full MCP server setup, config, and sink details, see packages/mcp/README.md.
Quick Start (Repo)
Run MCP server locally with a sample config:
Run dashboard locally:
MCP Config Model
Top-level config file is JSON and supports:
- schema for fully custom log_record properties, or
- schema_profile for built-in profile files in packages/mcp/examples/schema_profiles
- user_name for server-side user identity injection into persisted records
- sink for destination settings (jsonl, webhook, postgres)
Do not set both schema and schema_profile together.
Default behavior when omitted:
- schema: built-in default (agent_id, timestamp, work_summary, additional)
- sink: jsonl
- output file: ~/.agent-breadcrumbs/logs.jsonl
- Source
- awesome ยท https://github.com/ejcho623/agent-breadcrumbs
- Browse by field
- MCP servers
- Traction
- 4 โ
- added
- yesterday
More in MCP servers
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.