A shared, persistent filesystem for coding agents and teams, backed by SurrealDB. It also connects to Spectron memory and adds tools plus a /brain skill.

Use it to share project files between agents and team members, and to retain related project memory.

It keeps files and agent context available across sessions and collaborators instead of leaving them in one temporary workspace.

surrealfs — Plugin for Claude Code by surrealdb

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.

Clone the repo

git clone --depth 1 https://github.com/surrealdb/surrealfs

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/surrealdb/surrealfs/claude/github.svg)](https://agentmods.dev/plugins/surrealdb/surrealfs/claude)

Your own site

<a href="https://agentmods.dev/plugins/surrealdb/surrealfs/claude"><img src="https://agentmods.dev/badge/plugins/surrealdb/surrealfs/claude/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/surrealdb/surrealfs/claude"><img src="https://agentmods.dev/badge/plugins/surrealdb/surrealfs/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 2 skills, 1 MCP server cost 172 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

surrealfs 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 5d 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.

surrealfs/integrations/claude/.claude-plugin/plugin.json · 15 lines

The source is not reproduced here

No licence file

Read it on GitHub

Contents

What it installs

The manifest is a name and a version. 2 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 172 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

5d ago Changed 636f2d65a551
6d ago First seen · 15 lines scan A 89762cdbfce0

Subscribe to this mod's changes

surrealfs is a plugin published in the GitHub repository surrealdb/surrealfs (24 stars, last pushed 5d ago), with no licence file. 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 2026-09-08.

Databases Memory and context

mcp-neo4j

MCP configuration declaring 4 servers: mcp-neo4j-cloud-aura-api, mcp-neo4j-cypher, mcp-neo4j-data-modeling, mcp-neo4j-memory.

neo4j-contrib/mcp-neo4j · not measured

gnosis

Zero-config knowledge base MCP server — search, manage, and embed documentation (SQLite default, PostgreSQL optional).

nicholasglazer/gnosis-mcp · not measured

subrosa

Persistent, private memory for Claude Code — every session archived into a local, searchable SQLite database. What's said under the rose stays under the rose.

ij5a/subrosa · not measured

kauri

Kauri — a deterministic record database for LLM agents and humans. Tracks project decisions with structured lifecycle semantics, file-based staleness detection, and full-text search.

mhashim6/kauri · not measured

nlqdb-memory

Persistent, queryable memory for your agent: a real Postgres it asks in plain English over MCP, so it can GROUP BY / JOIN / aggregate over what it remembered instead of recalling the nearest few rows. Bundles the hosted MCP server plus two skills that teach the agent when to use it.

nlqdb/nlqdb · not measured

n3mc-workingmemory

Ephemeral (7-day TTL) hybrid vector + BM25 memory server for Claude Code, backed by Redis Stack. Multilingual out of the box (NFKC + CJK / Hangul / Thai / Lao / Myanmar / Khmer bigram + diacritic fold). Prerequisites: (1) Redis Stack running on localhost:6379 (docker run -d --name redis-stack -p 6379:6379…

NeuralNexusNote/n3mcmcp-lite · not measured