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/vasuag09/harness-claudeWrote 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/vasuag09/harness-claude/memory)<a href="https://agentmods.dev/mcp/vasuag09/harness-claude/memory"><img src="https://agentmods.dev/badge/mcp/vasuag09/harness-claude/memory/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/vasuag09/harness-claude/memory"><img src="https://agentmods.dev/badge/mcp/vasuag09/harness-claude/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
memory 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.
This is a copy
92% identical to memory — 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
{
"memory": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}What else .mcp.json configures
This page is one entry in a file that holds 3. 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 First seen · 9 lines scan A 2ab64fbe22b4
memory is an MCP server published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 3mo ago), 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 92% identical to memory, differing in 2 lines, and is treated as a copy.
Other mcp servers, from other repositories
thread-keeper
Multi-agent shared brain across Claude Code/Desktop, Codex, Antigravity CLI, Copilot, and VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server. Runs locally from the threadkeeper Python package.
usrcp
Encrypted local ledger of structured user state, shared across every MCP-aware AI tool. Runs locally from the usrcp npm package. Needs 1 environment variable to run.
reflect-mcp
Reflection's autonomous runtime — wake, read prior state, do useful work, write back, sleep. Runs locally from the reflect-mcp Python package.
june-mcp
MCP server for Junê — give any MCP agent (Claude Desktop, Claude Code, …) a shared, cited knowledge-graph memory backed by a June endpoint. Runs locally from the june-mcp Python package. Needs 13 environment variables to run.
engram
Persistent storage for local modules. Runs locally from the engram npm package.
engram
Your local, private memory layer. Index your notes and files, then recall anything with citations and temporal reasoning — 100% on your machine. Runs locally from the @jnmetacode/engram npm package.