surrealmcp
SurrealMCP -- Model Context Protocol server for SurrealDB. Lets MCP-compatible LLM hosts (Claude Desktop, Cursor, GitHub Copilot in VS Code, Zed, n8n) read and write a SurrealDB instance through a single config entry instead of bespoke per-agent integration code. Part of the surreal-skills collection.
What this skill does
# SurrealMCP -- MCP Server for SurrealDB
SurrealMCP exposes SurrealDB as a Model Context Protocol server so any
MCP host can query, mutate, introspect, and manage cloud instances
through one declarative config entry instead of bespoke per-agent
integration code.
> **v1.4.1 status note:** the v1.4.0 quick-start documented an
> install path, CLI shape, env vars, and tool catalog that did not
> match upstream. This file has been corrected against
> `surrealdb/surrealmcp/README.md`. For full detail see
> [rules/surrealmcp.md](../../rules/surrealmcp.md).
## Quick Start
`surrealmcp` is **not** published to crates.io or npm. Install from
source or use the official Docker image:
```bash
# From source
git clone https://github.com/surrealdb/surrealmcp
cd surrealmcp
cargo install --path .
# Docker (preferred)
docker run --rm -i --pull always surrealdb/surrealmcp:latest start
# Run as stdio server (the host launches this command)
surrealmcp start \
--endpoint ws://localhost:8000/rpc \
--ns test --db test \
--user root --pass root
```
The `start` subcommand is mandatory; `surrealmcp serve` and bare
`surrealmcp` (no subcommand) are not valid invocations.
## Host Config Snippet
Different MCP hosts use different top-level keys -- always consult the
host's own MCP docs for the exact shape. The Docker invocation works
across most hosts that follow the `mcpServers` convention:
```json
{
"mcpServers": {
"SurrealDB": {
"command": "docker",
"args": [
"run", "--rm", "-i", "--pull", "always",
"surrealdb/surrealmcp:latest",
"start"
],
"env": {
"SURREALDB_URL": "ws://localhost:8000/rpc",
"SURREALDB_NS": "test",
"SURREALDB_DB": "test",
"SURREALDB_USER": "root",
"SURREALDB_PASS": "root"
}
}
}
}
```
Note the env var names: `SURREALDB_*` (not `SURREAL_*`). Server-side
tuning uses a separate `SURREAL_MCP_*` prefix.
## Exposed Tools
The upstream README groups tools as:
- **Database operations:** `query`, `select`, `insert`, `create`,
`upsert`, `update`, `delete`, `relate`
- **Connection management:** `connect_endpoint`, `use_namespace`,
`use_database`, `list_namespaces`, `list_databases`,
`disconnect_endpoint`
- **Cloud operations:** `list_cloud_organizations`,
`list_cloud_instances`, `create_cloud_instance`, `pause_cloud_instance`,
`resume_cloud_instance`, `get_cloud_instance_status`
Tool wire-names are snake_case. Read-only tools are safe for
autonomous loops; mutating tools should be gated through the host's
permission prompt against shared / production DBs.
## Production Notes
- HTTP mode behind TLS + bearer JWT (validated via JWKS) for remote
hosts; never expose stdio publicly.
- Run MCP as a scoped DB user (`DEFINE USER ... ON DATABASE`), not root.
- Health check is HTTP: `curl http://localhost:8000/health`.
- Configure logging via `RUST_LOG` (the binary uses `tracing-subscriber`).
- Rate limit with `--rate-limit-rps` / `--rate-limit-burst`.
## Full Documentation
- **[rules/surrealmcp.md](../../rules/surrealmcp.md)** -- verified
install / CLI / env-var / tool catalog detail
- **[surrealdb/surrealmcp](https://github.com/surrealdb/surrealmcp)** --
upstream repository (source-of-truth README)
- **[modelcontextprotocol.io](https://modelcontextprotocol.io)** --
MCP specification
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.