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/martineserios/thebranaWrote 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/martineserios/thebrana/ruflo)<a href="https://agentmods.dev/mcp/martineserios/thebrana/ruflo"><img src="https://agentmods.dev/badge/mcp/martineserios/thebrana/ruflo.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
ruflo 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 8d 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
{
"ruflo": {
"command": "${HOME}/enter_thebrana/thebrana/system/scripts/ruflo-mcp.sh",
"args": [
"mcp",
"start"
],
"instructions": "Ruflo is the memory backbone, NOT an agent backbone — the agentic MCP surface (agent_execute/agent_spawn/swarm_*/hive-mind_*/coordination_*/autopilot_*) is bookkeeping-only under subscription, never use it for execution (ADR-059). Namespaces: 'knowledge' (facts, patterns, learnings — use for recall and storage), 'pattern' (reusable code/skill patterns — use for cross-session promotion), 'session' (ephemeral session state — query with threshold 0.55+, never use namespace 'all' below 0.55 as session records score constant 0.5 and contaminate results). Core tools: memory_search (recall), memory_store (persist), pattern-search/store (skill patterns). Claims: claims_claim/release/mark-stealable (advisory task locking). Sanctioned execution: testgen_tdd_repair — the one genuinely subscription-native MCP execution path (spawns claude -p, budget-capped, test-verified; branch on data.repaired, never success). Broken on this install: agentdb_hierarchical-store/recall and the wider agentdb_* bridge (ControllerRegistry duplicate-export crash, t-2757) — use memory_search/memory_store instead. Stub tools to avoid (not implemented): aidefence_*, ruvllm_*, wasm_agent_prompt, daa_*, embeddings_rabitq_*.",
"env": {
"MCP_CONNECTION_NONBLOCKING": "1"
}
}
}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.
- 8d ago First seen · 13 lines scan A e0872eb0376b
ruflo is an MCP server published in the GitHub repository martineserios/thebrana (3 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
hypermnesia-mcp-viz
Visualization and graph MCP server for Cortex — neural graph, methodology map, workflow graph, and trace UI extracted from the Cortex memory engine. Runs locally from the hypermnesia-mcp-viz Python package.
furl
MCP server "furl" as configured in omar-y-abdi/furl-ctx. Launched with sh -c PATH="$PATH:$HOME/.local/bin:$HOME/.cargo/bin:/opt/homebrew/bin:/usr/local. Needs 3 environment variables to run.
astral-recall
MCP server "astral-recall" as configured in sourikduttanyu/astral. Runs servers/astral_recall_mcp.py with python3.
dt
DomainTome — the living knowledge graph for your software project. A programmatic MCP-backed graph of business logic, flows, events and rules. Runs locally from the domaintome Python package.
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
component-explorer
MCP server "component-explorer" as configured in microsoft/vscode. Launched with npm exec --no -- component-explorer mcp -p ./test/componentFixtures/component-ex.