mcp-server-toolkit
Provides read-only SQLite integration with tools for inspecting database schemas and running single SELECT/WITH/EXPLAIN queries, returning results as Markdown tables and structured rows.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mcp-server-toolkit
A Model Context Protocol server that gives AI agents (Claude Desktop, Claude Code, any MCP client) data tools: read-only SQL, CSV profiling, JSON queries, web fetch and text diffs. It is built for the failure mode that matters with agents: a prompt-injected model calling your tools. Every tool is sandboxed, read-only and tested against the attacks.

Tools
Tool | What it does | Guardrails |
| Tables, columns and row counts of a SQLite file | Read-only connection |
| One SQL query, results as a Markdown table plus structured rows | Read-only connection and a single |
| Row count, inferred types, nulls, uniques, ranges, top values, sample rows | Sandboxed path, 20 MB cap |
| JMESPath over a JSON document | Input size cap; parse and expression errors returned to the model |
| Unified diff and word-level change counts | Input size cap |
| Public web page as readable text | SSRF protection on every hop, http(s) only, no credentials in URLs, 2 MB cap, 10 s timeout, max 3 redirects |
Plus a toolkit://files resource (what is available), a toolkit://file/{path} template, and
an explore_dataset prompt that makes the model profile before it queries and show its
evidence. All tools carry readOnlyHint; only fetch_url is openWorldHint.
Related MCP server: Universal Safe Database MCP Toolbox
Quick start
Claude Desktop (claude_desktop_config.json) or any MCP host:
{
"mcpServers": {
"data": {
"command": "npx",
"args": ["-y", "github:joaofrancowork/mcp-server-toolkit", "--root", "/path/to/your/data"]
}
}
}Claude Code: claude mcp add data -- npx -y github:joaofrancowork/mcp-server-toolkit --root ./data
From source:
git clone https://github.com/joaofrancowork/mcp-server-toolkit && cd mcp-server-toolkit
npm ci && npm run build
npm run inspect # MCP Inspector against the example dataDocker (stdio): docker run -i --rm -v "$PWD/data:/data:ro" mcp-server-toolkit.
Options: --root <dir> (or MCP_TOOLKIT_ROOT), --no-fetch to disable the only network tool,
--audit-log <file> to append one JSON line per tool call (tool, arguments truncated to 200
characters, duration, error flag).
Architecture
flowchart LR
H[MCP host<br/>Claude Desktop · Claude Code] <-->|JSON-RPC over stdio| S[McpServer]
S --> T1[sqlite_*]
S --> T2[csv_profile]
S --> T3[json_query · text_diff]
S --> T4[fetch_url]
S --> R[resources · prompt]
T1 & T2 & R --> SB{{Sandbox<br/>realpath under --root}}
T1 --> RO{{read-only SQLite<br/>+ statement allow-list}}
T4 --> SSRF{{DNS resolve every hop<br/>block private ranges}}
SB --> FS[(your data dir)]Security model
The model is not trusted: anything it reads (a web page, a CSV cell) may contain instructions from an attacker. The tools assume that and limit the blast radius.
Filesystem. Paths are resolved to their real path before the prefix check, so
../, absolute paths and symlinks pointing outside--rootare refused. Only expected extensions are opened.SQL. Two independent layers: SQLite opens the file with
readOnly: true, and the query must be oneSELECT/WITH/EXPLAINwithout write,ATTACHorPRAGMAkeywords (string literals are ignored, soWHERE name = 'drop'still works).Network.
fetch_urlresolves the host and rejects private, loopback, link-local, CGNAT, multicast and IPv4-mapped IPv6 addresses (cloud metadata at169.254.169.254included). It does this again for every redirect, which is how most SSRF filters are bypassed.Errors are results. Expected failures come back as
isErrortool results with a readable message, so the model can correct itself instead of the session crashing.stdout is the protocol. Logs go to stderr only.
Testing
npm test # 38 tests through a real MCP client over an in-memory transport, coverage gate
npm run smoke # builds, spawns the server over stdio and calls a tool, as a host wouldThe tests cover the protocol surface (tools, resources, prompt), the behaviour of each tool and
the attacks: path traversal, symlink escape, SQL writes hidden in CTEs, multiple statements,
ATTACH, SSRF through private IPs, DNS answers that mix public and private addresses,
redirects to localhost, redirect loops and oversized responses.
CI runs lint (Biome), tsc --strict, tests on Node 22 and 24, the stdio smoke test, a Docker
build with an initialize handshake, and on a v* tag publishes a GitHub release with the
packed tarball.
Roadmap
Streamable HTTP transport with OAuth for remote deployments
Parquet support via DuckDB (read-only)
Per-tool rate limits and an audit log of tool calls
fetch_urlcontent extraction with Readability
License
MIT. The example data is generated by npm run examples and is fictional.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
JSON/YAML, regex, diff, JWT, SQL dialects — the keyless millisecond ops an agent needs mid-task.
Safety tools for AI agents: safe page reader, prompt-injection, secrets, PII and MCP server scans
Agent tools for discovery, payment safety, data extraction, and DeFi.
PDF, image, video, OCR, screenshot, SQL, QR and text tools for agents. No API key, no signup.
Related MCP Servers
- FlicenseAqualityBmaintenanceEnables AI agents to safely interact with GitHub, query Postgres read-only, check deployment status, and search/read files within an allowlisted sandbox—all with dry-run writes and SQL/path safety gates.8-
- AlicenseNot gradedqualityCmaintenanceEnables AI models to securely analyze SQLite datasets and read local text documents through a local stdio interface. It provides read-only querying, schema discovery, pagination, and timeout protections to prevent data leaks or destructive changes.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to inspect database schemas and run strictly read-only SQL queries with guardrails against destructive statements, multi-statement chaining, and unbounded scans. Supports SQLite natively and PostgreSQL optionally.4137 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to explore and query SQLite databases through read-only tools for listing databases, inspecting tables, searching values, and running single SELECT statements. Layered defenses—static SQL parsing, read-only connections, an authorizer, query timeouts, and row caps—ensure models cannot modify data even if they try.MIT