Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/fantasyce/agent-recall-trailWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/fantasyce/agent-recall-trail/agent-recall-trail-agent-recall-trail)<a href="https://agentmods.dev/mcp/fantasyce/agent-recall-trail/agent-recall-trail-agent-recall-trail"><img src="https://agentmods.dev/badge/mcp/fantasyce/agent-recall-trail/agent-recall-trail-agent-recall-trail/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/fantasyce/agent-recall-trail/agent-recall-trail-agent-recall-trail"><img src="https://agentmods.dev/badge/mcp/fantasyce/agent-recall-trail/agent-recall-trail-agent-recall-trail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-recall-trail scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"agent-recall-trail": {
"command": "/bin/sh",
"args": [
"scripts/launch-mcp.sh",
"mcp",
"serve",
"--agent",
"codex-primary"
],
"cwd": "."
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · +2 lines 8651124e9cd5
- 11d ago First seen · 11 lines scan A d842cc011542
agent-recall-trail is an MCP server published in the GitHub repository fantasyce/agent-recall-trail (0 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
agent-fact-system
MCP server "agent-fact-system" as configured in leoge007/agent-fact-system. Runs locally from the agent-fact-system Python package.
mcp
Model Context Protocol server for Citadel: encrypted memory as MCP tools. Runs locally from the citadeldb-mcp Python package. Needs 1 environment variable to run.
wanyimem
A local memory system for coding agents that stores past interactions and retrieves relevant information later. It runs through MCP, a standard way for AI tools to connect to programs.
delx-memory
Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe. Runs locally from the delx-memory npm package. Needs 5 environment variables to run.
knowit
Shared team memory for AI coding agents — MCP server and CLI for persistent, queryable knowledge across sessions and teammates. Runs locally from the knowit npm package.
memory-ferry
Local-first, folder-synced long-term memory and reusable skills for AI agents. Runs locally from the memory-ferry npm package.