← Back to search

@falkordb/mcpserver

GitHub Actions Scanned 5d ago

Model Context Protocol server for FalkorDB graph databases - enables AI assistants to query and manage graph data using natural language

B
75 / 100

Versions

1.3.0latest
Jul 1, 2026
1.2.3
Jun 30, 2026
1.2.2
Apr 28, 2026
1.2.1
Feb 23, 2026
1.2.0
Feb 23, 2026
+ show 3 moreshow less
1.1.1
Feb 23, 2026
1.1.0
Feb 23, 2026
1.0.1
Feb 23, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 7

query_graph_readonly
annotations: none low

Run a read-only OpenCypher query on a graph using GRAPH.RO_QUERY. This ensures no write operations are performed and is ideal for replica instances.

list_graphs
annotations: none low

List all graphs available to query

delete_graph
annotations: none low

Permanently delete a graph from the database. WARNING: This action is irreversible. You must set confirmDelete to true to proceed.

query_graph
annotations: none low

Run an OpenCypher query on a graph. Supports both read-write and read-only queries.

get_graph_schema
annotations: none low

Get the schema of a graph including node labels, relationship types, and (optionally) the connection topology between them, to understand the graph structure before executing a query. Connection topology is derived from a bounded sample of relationships and can be disabled via includeConnections on very large graphs.

get_node_schema
annotations: none low

Sample up to N nodes of a given label and aggregate their property keys by how many nodes carry each one (descending). Interpret each property's frequency relative to the returned sampledCount (the actual number of nodes sampled, which may be less than requestedSampleSize) to detect naming drift — e.g. a property present on only a few of many sampled nodes likely duplicates another under a slightly different name. Especially valuable in schemaless graphs where property naming can drift across subsets of nodes.

get_relationship_schema
annotations: none low

Sample up to N relationships of a given type and aggregate their property keys by how many relationships carry each one (descending). Interpret each property's frequency relative to the returned sampledCount (the actual number of relationships sampled, which may be less than requestedSampleSize) to detect naming drift — e.g. a property present on only a few of many sampled relationships likely duplicates another under a slightly different name. Especially valuable in schemaless graphs where property naming can drift across subsets of relationships.

Permissions 1

env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 26

info
Tool: delete_graph manifest_parser · 85%
info
Tool: get_graph_schema manifest_parser · 85%
low
Tool 'query_graph' has no annotations annotation_checker · 100%
low
Tool 'query_graph_readonly' has no annotations annotation_checker · 100%
low
Tool 'list_graphs' has no annotations annotation_checker · 100%
low
Tool 'delete_graph' has no annotations annotation_checker · 100%
low
Tool 'get_graph_schema' has no annotations annotation_checker · 100%
low
Tool 'get_node_schema' has no annotations annotation_checker · 100%
low
Tool 'get_relationship_schema' has no annotations annotation_checker · 100%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.17.0 (GHSA-345p-7cg4-v4c7) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.17.0 (GHSA-8r9q-7v3j-jr4g) dependency_analyzer · 95%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.17.0 (GHSA-w48q-cv73-mx4w) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
Tool: query_graph manifest_parser · 85%
info
Tool: query_graph_readonly manifest_parser · 85%
info
Tool: list_graphs manifest_parser · 85%
info
Tool: get_node_schema manifest_parser · 85%
info
Tool: get_relationship_schema manifest_parser · 85%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (11) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
low
Permission: env_vars access detected permission_analyzer · 90%
critical
Tool poisoning in 'delete_graph': Directive language: 'you must' poisoning · 85%
info
SBOM generated: 503 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%