Loading…
Provides access to Drosophila melanogaster neuroscience data including neuroanatomy, neural connectivity, and gene expression from the VirtualFlyBrain knowledge base.
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 vfb3-mcp-server MCP server exposes 9 tools, focused primarily on database capabilities. Its published description reads: "Provides access to Drosophila melanogaster neuroscience data including neuroanatomy, neural connectivity, and gene expression from the VirtualFlyBrain knowledge base". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates vfb3-mcp-server F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Hidden instructions in a tool description" and "Hidden instructions in a tool description". 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 vfb3-mcp-server's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add vfb3-mcp-server to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://vfb3-mcp.virtualflybrain.orgStreamable 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.
Get term info for a VFB or anatomy ontology entity (VFB_*, FBbt_*, etc.). THIS IS THE QUERY DISCOVERY TOOL: the response's "Queries" array lists the valid query_type values that run_query accepts for
Run a pre-computed query on a VFB entity. REQUIRED WORKFLOW: (1) call get_term_info on the ID first; (2) read the response's "Queries" array; (3) pass one of those values as query_type. Calling run_qu
Search VFB terms. This is the search virtualflybrain.org itself runs — the same Solr query, the same ranking — so what comes back first here is what a user would see first on the site. USE filter_type
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: resolve_entity
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
, and synonyms. IMPORTANT: When match_type is SYNONYM or BROAD, always conRecommendationRemove model-directed instructions from tool descriptions.
tool: resolve_combination
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
lele IDs/names. IMPORTANT: When match is via synonym, confirm the resolvedRecommendationRemove model-directed instructions from tool descriptions.
tool: get_term_info
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
fo call in this conversation. Returns: SuperTypes (classification), Tags (daRecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_term_info
A tool description tries to alter the model’s use of another tool.
ype values that run_query accepts for this entity. ALWAYS call get_term_iRecommendationDescriptions must describe only their own tool.
tool: get_term_info
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.
or this entity. ALWAYS call get_term_info before run_query unless you already obtained the queryRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: run_query
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
er in this same conversation, returned a result that was clearly wrong, stalRecommendationRemove side-channel parameters; constrain tool inputs.
tool: run_query
A tool description tries to alter the model’s use of another tool.
KFLOW: (1) call get_term_info on the ID first; (2) read the response's "QueriRecommendationDescriptions must describe only their own tool.
tool: run_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 "query_type"RecommendationExpose parameterised operations instead of a raw query string; never build queries from unvalidated model output.
tool: search_terms
A tool description tries to alter the model’s use of another tool.
st instead of removing them. If the search returns no good matches, do NORecommendationDescriptions must describe only their own tool.
tool: search_terms
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: list_search_facets
A tool description tries to alter the model’s use of another tool.
tead of guessing: there are over 200 names, they are the index's own annotRecommendationDescriptions must describe only their own tool.
tool: resolve_entity
A tool description tries to alter the model’s use of another tool.
class IDs) use search_terms instead.RecommendationDescriptions must describe only their own tool.
tool: list_connectome_datasets
A tool description tries to alter the model’s use of another tool.
s arguments for query_connectivity. Common datasets include Hemibrain (hb), FAFB (RecommendationDescriptions must describe only their own tool.
tool: query_connectivity
A tool description tries to alter the model’s use of another tool.
tead of returning every neuron pair.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: get_term_info
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "get_term_info"RecommendationScope tools to the minimum needed.
tool: get_term_info
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.
e Images field: https://v2.virtualflybrain.org/org.geppetto.frontend/geppetto?id=<VFB_ID>&i=<TEMPLATE_ID>,<IMAGE_ID1>,<…RecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
tool: query_connectivity
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "query_connectivity"RecommendationScope tools to the minimum needed.
tool: run_query
An unusually long description is a common injection-padding tactic.
description length 2194 charsRecommendationKeep descriptions concise.
tool: search_terms
An unusually long description is a common injection-padding tactic.
description length 2574 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.
List the type names search_terms can filter, exclude, boost or demote by, with the number of terms carrying each one. Call this instead of guessing: there are over 200 names, they are the index's own
Resolve an unresolved FlyBase-related query string into VFB/FlyBase IDs and metadata. Pass the raw text exactly as the user wrote it (for example "P{VT054895-GAL4.DBD}", "Hb9-GAL4", "SS04495", "MB002B
Resolve an unresolved split-GAL4 combination name or synonym into its FBco ID and component hemidrivers. Pass the raw combination text exactly as the user wrote it (for example "MB002B" or "SS04495").
List available connectome datasets with their labels and symbols. Use the returned symbols when constructing exclude_dbs arguments for query_connectivity. Common datasets include Hemibrain (hb), FAFB
Query synaptic connectivity between Drosophila neuron classes across ALL connectome datasets simultaneously for comparative connectomics. This is NOT pre-cached — it runs live queries, so expect slow
Build a hierarchy tree for a VFB term, showing ancestors (parents) and/or descendants (children). Use relationship "part_of" for brain region structure (e.g. "what are the parts of the mushroom body?"