Loading…
Query the L-functions and Modular Forms Database with 9 read-only tools for SQL access, table schemas, and bulk CSV/JSONL export via a hosted SSE endpoint.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 8 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The LMFDB MCP server exposes 9 tools, focused primarily on database capabilities. Its published description reads: "Query the L-functions and Modular Forms Database with 9 read-only tools for SQL access, table schemas, and bulk CSV/JSONL export via a hosted SSE endpoint". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates LMFDB F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Unguarded destructive tools" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check LMFDB's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add LMFDB to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.lmfdb.org/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Curated map of the LMFDB (L-functions and Modular Forms Database) by mathematical area — ALWAYS CALL THIS FIRST for any task involving number theory data. Covers these mathematical areas: elliptic cur
List LMFDB tables with metadata (section, notes) when available. If you're starting a new task, prefer overview() — it gives the same metadata grouped by mathematical area and is usually more useful.
Search LMFDB documentation for tables and columns matching the given keywords. Use this to discover which table or column contains a mathematical quantity you're looking for. This is typically the fir
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: overview
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
run_sql(query): execute a SELECT query - count_rows, sample_rows, table_stats: cRecommendationAnnotate destructive tools and require human approval.
tool: overview
A tool description tries to alter the model’s use of another tool.
escribe_table / list_tables — it usually shortcuts the whole discoveryRecommendationDescriptions must describe only their own tool.
tool: overview
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
ematical area — ALWAYS CALL THIS FIRST for any task involving number theory data.RecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: list_tables
A tool description tries to alter the model’s use of another tool.
ew task, prefer overview() — it gives the same metadata grouped by mRecommendationDescriptions must describe only their own tool.
tool: run_sql
A database tool exposes a query/sql parameter that is a free-form string with no allow-list or parameterisation constraint — a raw-string injection surface. A tool exposing structured filters or an `enum` of named queries does not fire.
unconstrained query parameter "sql"RecommendationExpose parameterised operations instead of a raw query string; never build queries from unvalidated model output.
tool: export_query
A tool description tries to alter the model’s use of another tool.
Compared to run_sql: - run_sql returns rows inline (capped atRecommendationDescriptions must describe only their own tool.
tool: export_query
A database tool exposes a query/sql parameter that is a free-form string with no allow-list or parameterisation constraint — a raw-string injection surface. A tool exposing structured filters or an `enum` of named queries does not fire.
unconstrained query parameter "sql"RecommendationExpose parameterised operations instead of a raw query string; never build queries from unvalidated model output.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
D of run_sql. It returns a short-lived download URL, keeping the data outRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: export_query
The description pairs a fetch imperative with a hardcoded external URL, letting the server relocate its real instructions off-metadata and mutate them after review. Fires only when a fetch verb and a URL co-occur, so benign documentation links do not.
"url": "https://.../download/<token>", "format": "csv",RecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
tool: export_query
An unusually long description is a common injection-padding tactic.
description length 2872 charsRecommendationKeep descriptions concise.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Show the column names, types, and (where available) documentation for a given LMFDB table. The output includes: - table_name - description: the contents of the knowl "tables.<table_name>", if any, des
Return a random sample of rows from a table to understand its contents. Args: table_name: The table to sample (e.g. "ec_curvedata"). n: Number of rows to return (default 5, max 50). Returns: JSON with
Run a read-only SQL SELECT query against the LMFDB database. This is the most flexible tool — use it for filtering, joining, aggregating, or computing statistics across LMFDB tables. Args: sql: A SELE
Count rows in a table, optionally with a WHERE clause. Args: table_name: The table to count (e.g. "ec_curvedata"). where: Optional WHERE clause without the WHERE keyword (e.g. "rank >= 2 AND conductor
Compute basic statistics for a numeric column in a table. For non-numeric columns, returns count and distinct count only. Args: table_name: The table (e.g. "ec_curvedata"). column: The column to analy
Prepare a bulk download of a SELECT query's results. Returns a short- lived URL that streams the full result set as CSV or JSONL — the data does NOT go through the MCP conversation, so this is the rig