Loading…
Multi-domain reference corpus where every answer cites its verified source, enabling agents to ground responses in authoritative data.
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 drillable MCP server exposes 9 tools, focused primarily on communication capabilities. Its published description reads: "Multi-domain reference corpus where every answer cites its verified source, enabling agents to ground responses in authoritative data". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates drillable F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Database tool takes a raw, unparameterised query". 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 drillable's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add drillable to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.drillable.comStreamable 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.
Define a concept/term from a domain's glossary (e.g. 'stir', 'crop-factor', 'roughness'). Routes to each domain's lookup_concept; pass `domain` to target one, omit to fan out. For entities/records use
Search the mounted corpora by query. Routes to each domain's search tool; pass `domain` to target one. Empty results are logged as gaps. For COMPUTED quantities (molar mass, age/date math, unit conver
Check claims against the corpora. SINGLE: verify({claim}) grounds one claim (core/verify truth-referee verdict where a domain surfaces it, else a corpus-grounding badge). RECEIPT: verify({claims:[…]})
List broad CATEGORIES or the COMPLETE set within ONE corpus — the shape `search` cannot serve (search returns a ranked, capped sample, not the whole set). Requires `domain`. Returns every category axi
A deterministic AGGREGATE over ONE corpus's COMPLETE set — the calculated-query shape ("how many X", "break X down by Y", "which is most common"). Requires `domain`; optional `filter` scopes the set (
Discover the fleet's deeper machinery. No args → every mounted domain with its verbs grouped by rung (lookup → composability → contested → frontier). With `domain` → that domain's full tool list with
Invoke a domain verb discovered via `describe`: call(domain, tool, args). Identical to the namespaced tool surface — every answer drills to its source; a miss is a typed abstention (logged as demand),
Register your user's standing interest in a question the corpus can't answer yet: when it becomes answerable, they get one email. Call this ONLY when the user themselves asked to be told — ask them fi
Fetch a drillable.com address and return its typed envelope (record, grades, abstains, related actions). Pass an address returned by `search`, or a link carried in another drill result — a same-host p
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: lookup
A tool description tries to alter the model’s use of another tool.
es/records use `search`. Abstains on a miss, which is logged as a gapRecommendationDescriptions must describe only their own tool.
tool: lookup
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 "query"RecommendationExpose parameterised operations instead of a raw query string; never build queries from unvalidated model output.
tool: search
A tool description tries to alter the model’s use of another tool.
that hint via `describe`/`call` rather than retrying search. Mounted coRecommendationDescriptions must describe only their own tool.
tool: search
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 "query"RecommendationExpose parameterised operations instead of a raw query string; never build queries from unvalidated model output.
tool: enumerate
A tool description tries to alter the model’s use of another tool.
one record use `lookup`/`search`. Discover a domain's facets via `descRecommendationDescriptions must describe only their own tool.
tool: compute
A tool description tries to alter the model’s use of another tool.
oglog, peppers, search-heuristics, tomatoes, solar-times, blood-alcohoRecommendationDescriptions must describe only their own tool.
tool: describe
A tool description tries to alter the model’s use of another tool.
rouped by rung (lookup → composability → contested → frontier). With `RecommendationDescriptions must describe only their own tool.
tool: call
A tool description tries to alter the model’s use of another tool.
discovered via `describe`: call(domain, tool, args). Identical to the naRecommendationDescriptions must describe only their own tool.
tool: notify_when_held
A tool description tries to alter the model’s use of another tool.
get one email. Call this ONLY when the user themselves asked to beRecommendationDescriptions must describe only their own tool.
tool: drill
A tool description tries to alter the model’s use of another tool.
ss returned by `search`, or a link carried in another drill result — aRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
arking-symbols, ssh-key-fingerprint, woodturning-lathe-speed, tableRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ssue one search/lookup for it rather than declining from the roster —RecommendationDescriptions 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: (server instructions)
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.
p tables are at https://drillable.com/?gaps=<domain>). Experts live at the frontier rung: ifRecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
tool: lookup
An unusually long description is a common injection-padding tactic.
description length 19911 charsRecommendationKeep descriptions concise.
tool: search
An unusually long description is a common injection-padding tactic.
description length 19777 charsRecommendationKeep descriptions concise.
tool: enumerate
An unusually long description is a common injection-padding tactic.
description length 20052 charsRecommendationKeep descriptions concise.
tool: compute
An unusually long description is a common injection-padding tactic.
description length 19820 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.