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/Dave-London/PareWrote 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/dave-london/pare/server-bazel-pare-http)<a href="https://agentmods.dev/mcp/dave-london/pare/server-bazel-pare-http"><img src="https://agentmods.dev/badge/mcp/dave-london/pare/server-bazel-pare-http/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/dave-london/pare/server-bazel-pare-http"><img src="https://agentmods.dev/badge/mcp/dave-london/pare/server-bazel-pare-http.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pare-http 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 9d 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.
This is a copy
91% identical to http — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"pare-http": {
"command": "npx",
"args": [
"-y",
"@paretools/http"
],
"env": {}
}
}What else server.json configures
This page is one entry in a file that holds 26. Installing the file brings all of them; each is measured and scanned on its own page.
- MCP server build A not measured
- MCP server cargo A not measured
- MCP server docker A not measured
- MCP server git A not measured
- MCP server github A not measured
- MCP server go A not measured
- MCP server http A not measured
- MCP server lint A not measured
- MCP server make A not measured
- MCP server npm A not measured
- MCP server pare-build A not measured
- MCP server pare-cargo A not measured
- MCP server pare-docker A not measured
- MCP server pare-git A not measured
- MCP server pare-github A not measured
- MCP server pare-go A not measured
- MCP server pare-lint A not measured
- MCP server pare-make A not measured
- MCP server pare-npm A not measured
- MCP server pare-python A not measured
- MCP server pare-search A not measured
- MCP server pare-test A not measured
- MCP server python A not measured
- MCP server search A not measured
- MCP server test A not measured
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.
- 9d ago First seen · 10 lines scan A eb1022f0c38b
pare-http is an MCP server published in the GitHub repository Dave-London/Pare (138 stars, last pushed today), licensed MIT. 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. It is 91% identical to http, differing in 2 lines, and is treated as a copy.
Other mcp servers, from other repositories
speclock
Enforce project constraints from CLAUDE.md, AGENTS.md, and .cursorrules before AI-generated edits, commands, and commits. Runs locally from the speclock npm package.
visor-mcp
Skill-Orchestrated Context Intelligence Engine for AI coding agents. Runs locally from the visor-mcp Python package.
render-useful-mcp
MCP server for the Render Public API: all 207 endpoints plus workflow tools. Runs locally from the render-useful-mcp npm package. Needs 5 environment variables to run.
render
A complete, production-grade Model Context Protocol server for the Render Public API — all 207 official endpoints plus higher-level workflow tools. Runs locally from the render-useful-mcp npm package. Needs 1 environment variable to run.
webhook
Receive, inspect, replay and deliver webhooks — with signature verification and agent triggers. Remote server at mcp.webhook.co.
opencode-export
MCP server "opencode-export" as configured in ZelinZhou-THU/opencode-export. Runs locally from the opencode-export Python package.