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/KonghaYao/periWrote 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/konghayao/peri/openspec)<a href="https://agentmods.dev/mcp/konghayao/peri/openspec"><img src="https://agentmods.dev/badge/mcp/konghayao/peri/openspec/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/konghayao/peri/openspec"><img src="https://agentmods.dev/badge/mcp/konghayao/peri/openspec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openspec 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
{
"openspec": {
"type": "http",
"url": "https://peri-mcpp-gateway.claude-code-best.workers.dev/openspec/mcp",
"cwd": "."
}
}What else .mcp.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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 Changed · -1 lines 3ad18c502585
- 1mo ago First seen · 8 lines scan A 452eccddee7c
openspec is an MCP server published in the GitHub repository KonghaYao/peri (242 stars, last pushed today), 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 2026-08-30.
Other mcp servers, from other repositories
ctxfeed
MCP server "ctxfeed" as configured in SuperMarioYL/ctxfeed. Runs locally from the ctxfeed Python package.
tokensave
MCP server "tokensave" as configured in inercia/mitto. Launched with /opt/homebrew/bin/tokensave serve.
grok-subagent
MCP server "grok-subagent" as configured in Walvez/grok-subagent. Runs ./mcp-server/server.mjs with node.
codex-deepseek-worker
MCP server "codex-deepseek-worker" as configured in prelearn-code/deepseek-mcp. Runs locally from the codex-deepseek-worker Python package.
antigravity_glm_mcp
MCP server "antigravityglmmcp" as configured in coreline-ai/antigravityglmmcp. Runs locally from the antigravity_glm_mcp Python package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.