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.
npx skills add yedanyagamiai-cmd/openclaw-mcp-servers --skill openclaw-database-toolkitgit clone --depth 1 https://github.com/yedanyagamiai-cmd/openclaw-mcp-serversWrote 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/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-database-toolkit)<a href="https://agentmods.dev/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-database-toolkit"><img src="https://agentmods.dev/badge/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-database-toolkit/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/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-database-toolkit"><img src="https://agentmods.dev/badge/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-database-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00128 | $0.02567 |
| Opus 5.5 | $0.00051 | $0.01027 |
| Sonnet 5.5 | $0.00026 | $0.00513 |
| Haiku 4.5 | $0.00013 | $0.00257 |
Grade A, and why
openclaw-database-toolkit 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Database Toolkit v2.0
Database operations for AI agents. 5 tools. D1, PostgreSQL, MongoDB. Zero driver installs. Natural language queries.
| Tool | Purpose | Free |
|---|---|---|
query_database |
Execute SELECT queries or natural language queries against any connected DB | Yes |
insert_records |
Insert one or many records into any table with type validation | Yes |
update_records |
Update records matching a WHERE clause or natural language condition | Pro |
get_schema |
Retrieve full schema for a database or specific table | Yes |
migrate_schema |
Run DDL migrations: CREATE TABLE, ADD COLUMN, CREATE INDEX | Pro |
What's New in v2.0
- DataBridge Protocol -- Unified query interface across D1 (Cloudflare SQLite), PostgreSQL (any host), and MongoDB Atlas. One tool, three databases.
- NLQ Engine -- Natural Language Query: describe what you want in English, get SQL or MQL back plus results. No SQL knowledge required.
- SafeWrite Guard -- Destructive operations (DELETE, DROP, TRUNCATE) require an explicit
confirm: trueflag. No accidental data loss. - SchemaCache -- Table schemas are cached for 5 minutes. get_schema is instant after the first call in a session.
Quick Start
{
"openclaw-database-toolkit": {
"type": "streamable-http",
"url": "https://openclaw-database-toolkit-mcp.yagami8095.workers.dev/mcp"
}
}
Add to Claude Desktop, Cursor, Windsurf, VS Code, or any MCP-compatible client. Zero install. Works immediately.
Detection Triggers
This skill activates when a user says any of these:
- "query my database", "run this SQL", "SELECT from", "D1 query", "database query"
- "insert records", "add rows to table", "bulk insert", "save to database", "write to DB"
- "update records", "UPDATE WHERE", "bulk update", "set this field", "update these rows"
- "show table schema", "what columns exist", "describe this table", "database schema"
- "add a column", "create table", "run migration", "schema migration", "ALTER TABLE"
- "D1 database", "PostgreSQL", "MongoDB Atlas", "Cloudflare D1", "SQL query"
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.
- 1mo ago First seen · 211 lines · 128 tokens per session scan A eff8410e7d51
openclaw-database-toolkit is a skill published in the GitHub repository yedanyagamiai-cmd/openclaw-mcp-servers (4 stars, last pushed 7mo ago), licensed MIT. It adds 128 tokens to every session and 2,567 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
database-expert
Advanced database design and administration for PostgreSQL, MongoDB, and Redis. Use when designing schemas, optimizing queries, managing database performance, or implementing data patterns.
agent-database-expert
Specialist subagent: Expert database architect and engineer for PostgreSQL, MongoDB, Redis, and all major databases. Use when designing schemas, optimizing queries, planning migrations, implementing caching, or troubleshooting database performance.
vector-backend-operations
Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.