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/myelixlabs/synapse-mcpWrote 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/plugins/myelixlabs/synapse-mcp/claude-plugin)<a href="https://agentmods.dev/plugins/myelixlabs/synapse-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/myelixlabs/synapse-mcp/claude-plugin/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/plugins/myelixlabs/synapse-mcp/claude-plugin"><img src="https://agentmods.dev/badge/plugins/myelixlabs/synapse-mcp/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
synapse-mcp 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 6d 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
{
"name": "synapse-mcp",
"displayName": "Synapse MCP",
"version": "4.3.0",
"description": "A persistent code-knowledge graph for AI agents. Runs locally. Writes safely.",
"author": {
"name": "Myelix Labs",
"email": "[email protected]",
"url": "https://synapse-mcp.dev"
},
"homepage": "https://synapse-mcp.dev",
"privacyPolicyUrl": "https://synapse-mcp.dev/privacy",
"repository": "https://github.com/myelixlabs/synapse-mcp",
"license": "MIT",
"keywords": [
"mcp",
"ast",
"codebase-graph",
"refactoring",
"safe-writes",
"token-savings",
"code-review"
],
"mcpServers": {
"synapse": {
"type": "http",
"url": "${user_config.synapse_url}"
}
},
"userConfig": {
"synapse_url": {
"type": "string",
"title": "Synapse MCP URL",
"description": "Where the Synapse MCP server installed on this machine listens. Keep the default unless you started Synapse on another port.",
"default": "http://127.0.0.1:8585"
}
}
}
What it installs
The manifest is a name and a version. 8 skills travel with it, and installing the plugin installs all of them — 314 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed 792c78727729
- 7d ago First seen · 39 lines scan A 30747ce5151b
synapse-mcp is a plugin published in the GitHub repository myelixlabs/synapse-mcp (3 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-30.
Other plugins, from other repositories
trace-mcp
Framework-aware code intelligence MCP server. 88 framework integrations, 81 languages, semantic search with Signal Fusion (BM25 + PageRank + embeddings + identity), refactoring tools (rename/move/extract/codemod), change-impact analysis, security scanning, and decision/session memory.
hunch
A git-native reasoning graph of decisions, bugs, and invariants for your codebase — queried and enforced at reasoning time. Adds the hunch MCP tools plus /hunch:capture, /hunch:heal, /hunch:why, /hunch:fix, /hunch:fragile.
sverklo-skill
Teaches Claude how to use sverklo's code intelligence MCP tools — semantic search, blast-radius, PR review, codebase audit, persistent memory.
codeindex
Skills that teach any agent to answer code questions structurally instead of reading whole files — symbol lookup, callers, imports and blast radius. Bundles the codeindex MCP server so install wires everything in one step.
claude-playbook
Engineering guardrails for Claude Code: path-scoped rules, review and verification skills, specialist subagents, and hooks that enforce what instructions only request.
easy-cheese
easy-cheese. Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit.