agentmods.dev

rewynd

A local connection to the rewynd service, started with its command-line interface. The input does not explain what operations this connection exposes.

In plain words
What is it for?
It may provide access to rewynd from a coding agent, but the input does not give enough information to say what jobs it supports.
Why use it?
The available description is too limited to identify a specific problem it removes or a reliable use case.

MCP server for Claude CodeCodexCursor

2 2mo ago A scan tokens not measured original MIT
View the source file SrinjoyDev/rewynd
Install

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.

agentmods
npx agentmods add mcp/srinjoydev/rewynd/claude-code-rewynd
Clone the repo
git clone --depth 1 https://github.com/SrinjoyDev/rewynd

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

rewynd 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 2d 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.

integrations/claude-code/.mcp.json · 8 lines

What it actually says

{
  "rewynd": {
    "command": "rewynd",
    "args": [
      "mcp"
    ]
  }
}
Changes

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.

  1. 2d ago First seen · 8 lines scan A c89c21b1e4b7

Subscribe to this mod's changes

rewynd is an MCP server published in the GitHub repository SrinjoyDev/rewynd (2 stars, last pushed 2mo 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DebuggingLanguagesai-agentsclideveloper-toolsdevtools
Related

Other mcp servers, from other repositories

orchestrator

MCP server "orchestrator" as configured in synaptixs/spine. Launched with orchestrator-mcp.

synaptixs/spine · not measured

aegis

Credential isolation for AI agents. Inject secrets at the network boundary. Runs locally from the @getaegis/cli npm package. Needs 11 environment variables to run.

getaegis/aegis · not measured

mcp-devtools

MCP server "mcp-devtools" as configured in rshade/mcp-devtools-server. Launched with ./start-mcp.sh. Needs 1 environment variable to run.

rshade/mcp-devtools-server · not measured

sigil

MCP server "sigil" as configured in NOMARJ/sigil. Runs locally from the @nomark/sigil-mcp-server npm package.

NOMARJ/sigil · not measured

yourmemory

Persistent memory for Claude — Ebbinghaus forgetting curve, semantic deduplication, MCP-native. Runs locally from the yourmemory Python package. Needs 1 environment variable to run.

sachitrafa/YourMemory · not measured

devloop

Browser + dev-server logs on one correlated timeline, for Claude Code and AI agents. Runs locally from the devloop-mcp npm package.

vincentvella/devloop · not measured