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/omar-y-abdi/furl-ctxInstalling this writes the configuration, not the program: `sh` has to be on your PATH already, or the server will not start.
Wrote 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/omar-y-abdi/furl-ctx/furl-codex-furl)<a href="https://agentmods.dev/mcp/omar-y-abdi/furl-ctx/furl-codex-furl"><img src="https://agentmods.dev/badge/mcp/omar-y-abdi/furl-ctx/furl-codex-furl/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/omar-y-abdi/furl-ctx/furl-codex-furl"><img src="https://agentmods.dev/badge/mcp/omar-y-abdi/furl-ctx/furl-codex-furl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
furl 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 1mo 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
{
"furl": {
"command": "sh",
"args": [
"-c",
"PATH=\"$PATH:$HOME/.local/bin:$HOME/.cargo/bin:/opt/homebrew/bin:/usr/local/bin\" exec uv run --no-project --with 'furl-ctx[mcp]==1.4.0' python -m furl_ctx.ccr.mcp_server"
],
"env": {
"FURL_CCR_BACKEND": "sqlite",
"FURL_CCR_SPILL": "1",
"FURL_CCR_TTL_SECONDS": "86400"
}
}
}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.
- 1mo ago First seen · 14 lines scan A 9081069bbfe1
furl is an MCP server published in the GitHub repository omar-y-abdi/furl-ctx (5 stars, last pushed yesterday), 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
compendium-mcp
MCP server that compresses, summarizes, and filters context to minimize LLM token usage. Runs locally from the compendium-mcp npm package.
astral-recall
MCP server "astral-recall" as configured in sourikduttanyu/astral. Runs servers/astral_recall_mcp.py with python3.
tokenmizer
MCP server "tokenmizer" as configured in Shweta-Mishra-ai/tokenmizer. Launched with tokenmizer-mcp. Needs 2 environment variables to run.
bilinc
Cloud-only memory SDK and MCP adapter for autonomous agents. Runs locally from the bilinc Python package. Needs 1 environment variable to run.
lethe
Context garbage collector for long-running LLM agents — offload and recall to save tokens (Claude Code & Codex via MCP). Runs locally from the lethe-llm-context Python package. Needs 1 environment variable to run.
dt
DomainTome — the living knowledge graph for your software project. A programmatic MCP-backed graph of business logic, flows, events and rules. Runs locally from the domaintome Python package.