bhe_mcp
Provides tools for running Cypher queries on the BloodHound Enterprise Neo4j graph database, enabling attack path analysis, risk posture assessment, and exploration of Active Directory, Azure/Entra ID, and OpenGraph environments.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bhe_mcp Find the shortest path from user 'alice' to Domain Admins."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BloodHound Enterprise MCP
A Model Context Protocol (MCP) server that connects LLMs to BloodHound Enterprise. Ask questions in natural language, get attack path analysis, run Cypher queries, and explore Active Directory, Azure/Entra ID, and OpenGraph environments — all from your AI assistant.
Fork Attribution
This project is a fork of mwnickerson/bloodhound_mcp. The original project and its contributors created the BloodHound MCP foundation this fork builds on.
This fork modifies the original BloodHound Community Edition-focused implementation for BloodHound Enterprise API coverage, multi-tenant MCP configuration, expanded endpoint wrappers, Enterprise attack path/risk posture workflows, and BHE-specific documentation. The project remains licensed under GPL-3.0; see LICENSE and NOTICE.
Related MCP server: PentestMCP
How It Works
The server exposes BloodHound Enterprise's REST API and Neo4j graph through a set of composite MCP tools, reference resources, and a system prompt tuned for offensive security analysis.
Composite Tools
Each tool uses an info_type parameter to select what data is returned, keeping the tool surface small and token-efficient:
Tool |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Resources
Reference material the LLM loads on demand — no extra API calls:
Resource URI | Contents |
| Cypher syntax, schema, property names, patterns |
| Quick query-building syntax patterns |
| Supported BloodHound Cypher syntax, caveats, and unsupported constructs |
| Battle-tested templates: DCSync, Kerberoasting, GPO abuse, delegation, ADCS, shadow credentials, NTLM relay, and more |
| AD node types and relationships quick reference |
| Full AD attack methodology and workflow |
| Azure/Entra ID analysis quick reference |
| Full Azure attack chains |
| ADCS ESC1–ESC13 quick reference |
| Detailed ESC analysis and exploitation |
| Custom node schema design and best practices |
| SQL Server and Web App OpenGraph examples |
System Prompt
The bloodhound_assistant prompt includes behavioral rules that guide the LLM:
Load the offensive query library before writing Cypher for any attack scenario
Never draw privilege conclusions without checking group memberships and
admincountRespect BloodHound's property naming conventions (
hasspn,enabled,admincount— all lowercase)Handle uppercase name storage (
DOMAIN ADMINS@CORP.LOCAL) correctly in filtersFollow proper DCSync and GPO edge traversal patterns
Prerequisites
Python 3.11+
BloodHound Enterprise instance with data loaded
BloodHound API credentials (Token ID + Token Key)
Installation
git clone https://github.com/mwnickerson/bloodhound_mcp.git ~/git/bhe_mcp
cd ~/git/bhe_mcp
uv syncCreate a .env file in the project root:
BLOODHOUND_DOMAIN=your-bloodhound-instance.domain.com
BLOODHOUND_TOKEN_ID=your-token-id
BLOODHOUND_TOKEN_KEY=your-token-keyThe server defaults to https on port 443. Override if needed:
BLOODHOUND_PORT=8080
BLOODHOUND_SCHEME=httpConfiguration
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"bhe_mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/bhe_mcp",
"run",
"main.py"
]
}
}
}Claude Code
Add to ~/.claude/mcp.json:
{
"mcpServers": {
"bhe_mcp": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"/path/to/bhe_mcp",
"run",
"main.py"
]
}
}
}OpenAI Codex CLI
Add to ~/.codex/config.toml (or .codex/config.toml for project-scoped config):
[mcp_servers.bhe_mcp]
command = "uv"
args = ["--directory", "/path/to/bhe_mcp", "run", "main.py"]Since the server loads credentials from .env automatically, no env block is needed. If you prefer to pass them explicitly:
[mcp_servers.bhe_mcp]
command = "uv"
args = ["--directory", "/path/to/bhe_mcp", "run", "main.py"]
[mcp_servers.bhe_mcp.env]
BLOODHOUND_DOMAIN = "your-bloodhound-instance.domain.com"
BLOODHOUND_TOKEN_ID = "your-token-id"
BLOODHOUND_TOKEN_KEY = "your-token-key"For multiple BHE tenants, point each MCP server at the same checkout and give each one its own env file. This keeps demo and maplesyrup distinct by server name and by the codename in the env file path:
[mcp_servers.bloodhound_demo]
command = "uv"
args = ["--directory", "/path/to/bhe_mcp", "run", "main.py"]
[mcp_servers.bloodhound_demo.env]
UV_CACHE_DIR = "/path/to/uv-cache"
BLOODHOUND_ENV_FILE = "/path/to/bloodhound_demo.env"
[mcp_servers.bloodhound_maplesyrup]
command = "uv"
args = ["--directory", "/path/to/bhe_mcp", "run", "main.py"]
[mcp_servers.bloodhound_maplesyrup.env]
UV_CACHE_DIR = "/path/to/uv-cache"
BLOODHOUND_ENV_FILE = "/path/to/bloodhound_maplesyrup.env"MCP Inspector
Command:
uvArgs:
--directory /path/to/bhe_mcp run main.py
BloodHound API Token
Log into BloodHound Enterprise
Navigate to Administration → API Tokens
Create a new token and copy the Token ID and Token Key into your
.env
Usage
Example Queries
Reconnaissance:
What domains are in BloodHound?
Show me all Domain Admins in CORP.LOCAL
Find all kerberoastable users
Which computers have unconstrained delegation?User and Group Analysis:
What admin rights does jsmith@corp.local have?
Show me all sessions for the administrator account
What groups is this user a member of?
Who controls the IT ADMINS group?Attack Path Analysis:
Find the shortest path from jsmith@corp.local to Domain Admins
Who has DCSync rights in the domain?
Show me all GPO abuse paths
Find ADCS ESC1 paths in the domainCustom Cypher:
Run a Cypher query to find all users with SPN set and admincount=1
Find all computers where DOMAIN USERS can RDPOpenGraph Support
BloodHound 8.0+ supports custom node types via OpenGraph, letting you model non-AD infrastructure (cloud resources, databases, custom assets) in the same graph as Active Directory.
The custom_nodes tool handles legacy CRUD operations on node type display configurations through /api/v2/custom-nodes. For BloodHound v9.0.0+ instances with OpenGraph extension management enabled, the same composite tool also supports /api/v2/extensions and /api/v2/extensions-edges via extension_list, extension_upsert, extension_delete, and extension_edges.
Use the bloodhound://opengraph/guide and bloodhound://opengraph/examples resources for schema design and Cypher patterns. For structured OpenGraph schemas, upsert the extension schema first, then ingest collection data with file_upload.
Requires BloodHound 8.0 or later. OpenGraph extension management requires BloodHound 9.0.0+ and the corresponding feature flag to be enabled.
Security Considerations
BloodHound data processed through this tool is transmitted to your LLM provider's servers. Do not use this with production AD data unless you have assessed that risk.
Recommended use cases:
Lab environments (GOAD, DetectionLab, custom ranges)
Training and certification prep
Research and tool development
Non-production domain analysis
Best practices:
Rotate BloodHound API tokens regularly
Use a read-only API token where possible
Consider a local LLM bridge for sensitive environments
Testing
# Full test suite
uv run pytest
# Specific modules
uv run pytest tests/test_main_mcp_tools.py -v
uv run pytest tests/test_bloodhound_api.py -v
# Integration tests (requires a live BloodHound instance)
BLOODHOUND_INTEGRATION_TESTS=1 uv run pytest tests/test_integration.py -vContributing
Contributions are welcome. Open an issue to discuss significant changes before submitting a PR.
Fork the repo
Create a feature branch
Add tests for new functionality
Run
uv run pytestand confirm everything passesSubmit a pull request
Acknowledgments
SpecterOps for BloodHound
Orange Cyberdefense for GOAD (used for testing)
@jlowin for FastMCP
@xpn for MCP inspiration via the Mythic MCP project
License
GNU General Public License v3.0 — see LICENSE for details.
Available Tools
20 toolsadcs_infoA
QUery AD Certificate Services data from BloodHound object_id is the template_id or the ca_id depending on the info_type info_type options: cert_template_info - certificate template properties (object_id = template ID) cert_template_controllers - who can modify this template - key for ESC1/ESC2 (object_id = template ID) cert_template_published_to_cas - Enterprise CAs publishing this template root_ca_info - root ca properties (object_id = CA ID) root_ca_controllers - who controls the root ca - key for ESC4/ESC5 (object_id = CA ID) root_ca_pki_hierarchy - PKI hierarchy for a root CA enterprise_ca_info - enterprise CA properties (object_id = CA ID) enterprise_ca_controllers - who controls the enterprise CA - key for ESC3/ESC6 (object_id = CA ID) enterprise_ca_pki_hierarchy - PKI hierarchy for an enterprise CA enterprise_ca_published_templates - templates published to this enterprise CA aia_ca_info - AIA CA properties aia_ca_controllers - who controls the AIA CA (object_id = CA ID) aia_ca_pki_hierarchy - PKI hierarchy for an AIA CA nt_auth_store_info - NT Auth Store properties nt_auth_store_controllers - controllers of an NT Auth Store nt_auth_store_trusted_cas - trusted Enterprise CAs for an NT Auth Store
args:
object_id: Template ID or CA ID depending on info_type (required)
info_type: what to retrieve (required)
limit: Max Results (default 100, useful in large environments)
skip: Pagination offset (default 0)
Inputs: info_type (required), object_id (required), skip, limit.
asset_groupsA
Manage Asset isolation groups and tages in BloodHound
info_type options:
list - list all asset groups (optional filters: name, tag, sort_by, system_group)
get - get a specific asset group (requires: asset_group_id)
create - create a new asset group (requires: name, tag)
update - update an existing asset group (requires: asset_group_id)
delete - delete an asset group (requires: asset_group_id)
collections - list historical membership snapshots (requires: asset_group_id)
custom_selectors - get custom selector/member count (requires: asset_group_id)
members - list asset group members (requires: asset_group_id)
member_counts - get member counts by object type (requires: asset_group_id)
combo_node - get the combo tree for an asset group (requires: asset_group_id)
create_selectors - add auto membership selectors (requires: asset_group_id, selectors_json)
update_selectors - set auto membership selectors (requires: asset_group_id, selectors_json)
delete_selector - delete an asset group selector (requires: asset_group_id, asset_group_selector_id)
list_tags - list asset group tags (optional: name, tag, sort_by)
create_tag - create a new asset group tag (requires: name, tag)
tag_members - list members of a tag (requires: asset_group_tag_id)
tag_member_selectors - get selectors for a tag member (requires: asset_group_tag_id, asset_group_member_id)
tag_member_counts - get tag member counts (requires: asset_group_tag_id)
tag_selectors - list tag selectors (requires: asset_group_tag_id)
tag_selector_members - list members for a tag selector (requires: asset_group_tag_id, asset_group_tag_selector_id)
tag_selector_member_counts - count members for a tag selector (requires: asset_group_tag_id, asset_group_tag_selector_id)
preview_tag_selectors - preview selectors (requires: request_json)
search_tags - search asset group tags (requires: request_json)
tag_history - list tag history records
search_tag_history - search tag history records (requires: request_json)
certifications - get certifications for privilege zones
update_certifications - certify or revoke objects (requires: request_json)
args:
info_type: operation to perform (default: list)
asset_group_id: Asset group ID (for get, update, delete, collections, member_counts, update_selectors)
asset_group_tag_id: Tag ID (for tag_members)
name: Group/tag name (for create, update, create_tag, or filters)
tag: Tag value (for create, update, create_tag, or filters)
sort_by: Sort field (for list, list tags)
system_group: Filter by system group (for list)
selectors_json: JSON array of selector specs (for update_selectors)
request_json: JSON request body for preview/search/certification actions
skip: Pagination offset (default 0)
limit: Max results (default 100)
Inputs: tag, name, skip, limit, +10 more.
attack_pathsA
Query BloodHound Enterprise attack path data.
info_type options:
domain_findings - export attack path findings for a domain (needs: domain_id)
finding_trends - list attack path finding trends
types - list all attack path types
start_analysis - start attack path analysis
details - get all attack path findings with details
domain_available_types - list attack path types available in a domain (needs: domain_id)
domain_details - list attack path details for a domain (needs: domain_id)
domain_sparkline - list attack path sparkline values for a domain (needs: domain_id)
acceptance - update attack path risk acceptance (needs: attack_path_id, acceptance_json)
args:
info_type: what to retrieve or update (default: details)
domain_id: Domain object ID for domain-scoped attack path endpoints
attack_path_id: Attack path finding ID for risk acceptance
acceptance_json: JSON string or object accepted by the BHE risk acceptance API
finding_name: Case-insensitive filter for finding/type/name fields
source_name: Case-insensitive filter for source fields
target_name: Case-insensitive filter for target fields
environment_id: Case-insensitive filter for environment/domain fields
accepted: Filter findings by accepted/risk acceptance state
Inputs: accepted, domain_id, info_type, source_name, +5 more.
collection_infoA
Query BloodHound Enterprise collection infrastructure status.
info_type options:
collector_manifest - get collector manifest (needs: collector_type)
collector_checksum - get collector checksum (needs: collector_type, release_tag)
kennel_manifest - get kennel manifest
kennel_enterprise_manifest - get kennel enterprise manifest
clients - list clients
client - get a client (needs: client_id)
client_completed_tasks - list completed tasks for a client (needs: client_id)
client_completed_jobs - list completed jobs for a client (needs: client_id)
jobs_available - list available jobs
jobs_finished - list finished jobs
jobs - list jobs
job_current - get current job
job - get a job (needs: job_id)
job_log - get job log (needs: job_id)
tasks_available - list available tasks
tasks_finished - list finished tasks
tasks - list tasks
task_current - get current task
task - get a task (needs: task_id)
task_log - get task log (needs: task_id)
events - list scheduled events
event - get scheduled event (needs: event_id)
Inputs: skip, limit, job_id, task_id, +6 more.
computer_infoA
Query computer data from BloodHound. info_type options: info - general computer properties and attributes admin_rights - objects this computer has admin rights on admin_users - users/groups that have admin rights on this computer constrained_delegation - services this computer can delegate to via kerberos constrained_users - users with contained delegation TO this computer controllables - objects this computer can control controllers - principals that have control over this computer dcom_rights - machines this computer can execute DCOM on dcom_users - users/groups with DCOM rights ON this computer group_membership - groups this computer belongs to ps_remote_rights - machines this computer can PSRemote to ps_remote_users - users/groups with PSRemote rights ON this computer rdp_rights - machines this computer can RDP to rdp_users - users/groups with RDP rights ON this computer sessions - users with active sessions on this computer sql_admins - SQL servers this computer is admin on
args:
computer_id: BloodHound object ID of the computer (required)
info_type: what to retrieve (default: info)
limit: Max Results (default 100, useful in large environments)
skip: Pagination offset (default 0)
Inputs: computer_id (required), skip, limit, info_type.
custom_nodesA
Manage OpenGraph custom node display configs and v9 extension schemas. info_type options: list - list all custom node configs get - get details for a specific node kind (needs: kind_name) create - create new node kind with display metadata (needs: custom_types_json) update - update a node kind's display config (needs: kind_name, config_json) delete - delete a node kind (needs: kind_name) validate_icon - validate icon config before creating/updating (needs: icon_config_json) extension_list - list OpenGraph extensions (BloodHound v9+) extension_upsert - create/update extension schema (needs: extension_json or extension_file_path) extension_delete - delete extension schema by ID (needs: extension_id) extension_edges - list extension edge kinds (optional: schemas, is_traversable)
args:
info_type: what to retrieve (default: list)
kind_name: Custom node kind name (for get,update, delete)
custom_types_json: JSON string or object for creating a new node kind (for create)
config_json: JSON string or object for updating a node kind's display config (for update)
icon_config_json: JSON string or object for validating icon config (for validate_icon)
extension_json: JSON string or object for BloodHound v9 OpenGraph extension upsert
extension_file_path: local JSON file path for BloodHound v9 OpenGraph extension upsert
extension_id: OpenGraph extension ID for delete
schemas: schema name or list of schema names for extension edge filtering
is_traversable: bool or BloodHound filter string (for example: eq:true)
Inputs: schemas, info_type, kind_name, config_json, +6 more.
cypher_queryA
Execute and manage Cypher queries in BloodHound.
info_type options:
run - execute a cypher query (needs: query; optional: include_properties)
interpret - interpret a natural language query into cypher (needs: query, result_json)
list_saved - list saved queries (optional: name, skip, limit)
create_saved - save a new query (needs: name, query)
get_saved - get details of a saved query (needs: query_id)
update_saved - update an existing saved query (needs: query_id; optional: name, query, description)
delete_saved - delete a saved query (needs: query_id)
share_saved - share a saved query with other users (needs: query_id; optional: user_ids, public)
saved_permissions - get saved query permissions (needs: query_id)
export_saved - export a saved query (needs: query_id)
import_saved - import saved queries (needs: payload_json)
export_saved_many - export saved queries (optional: query_ids)
validate - validate a cypher query for syntax and semantics (needs: query)
args:
info_type: Operation to perform
query: Cypher query string (for run, create_saved, update_saved, validate)
include_properties: Include node/edge properties in results (for run, default: True)
name: Query name (for create_saved, update_saved, list_saved filter)
query_id: Saved query ID (for get_saved, update_saved, delete_saved, share_saved)
result_json: JSON result string from a previous run (for interpret)
description: Query description (for update_saved)
user_ids: Comma-separated user IDs to share with (for share_saved)
query_ids: Comma-separated saved query IDs to export
payload_json: JSON string/object for saved query import
public: Make query public (for share_saved, default: False)
limit: Max results (default 100)
skip: Pagination offset (default 0)
Inputs: info_type (required), name, skip, limit, +9 more.
data_qualityA
Query data quality and collection statistics from BloodHound info_type options: completeness - overall database completeness stats (no params needed) ad_domain - collection quality over time for an AD domain (needs: domain_id) azure_tenant - collection quality over time for an azure tenant (needs: tenant_id) platform - aggregate quality stats for a platform (needs: platform_id - "ad" or "azure")
args:
info_type: what to retrieve (default: completeness)
domain_id: AD domain ID
platform_id: "ad" or "azure"
start: Start datetime in RFC-3339 format
end: end datetime in RFC-3339 format
sort_by: Sort field - "created_at" or "updated_at" (optional)
skip: Pagination offset (default 0)
limit: max results (default 100)
Inputs: end, skip, limit, start, +5 more.
domain_infoA
Query domain level data from BloodHound info_type options: list - list all domains (no domain_id needed) info - domain entity info (needs domain_id) search - search objects by name/ID (needs query param, domain_id not needed) users - users in the domain groups - groups in the domain computers - computers in the domain controllers - security prinicpals with control relationships gpos - Group Policy Objects ous - Organizational unites dc_syncers - Principals with DCSync rights foreign_admins - admins from other domains foreign_gpo_controllers - GPO controllers from other domains foreign_groups - groups with cross domain members foreign_users - users referenced across domains inbound_trusts - domains that trust this domain outbound_trusts - domains this domain trusts linked_gpos - linked GPOs in this domain adcs_escalations - ADCS escalation findings in this domain Args: info_type: what to retrieve (default: list) domain_id: Domain object ID (required for most info_types) query: Search text (for info_type=search only) object_type: Filter by type - User, computer, Group, GPO, OU, Domain, AZUer, etc. (search only) limit: Max Results (default 100, useful in large environments) skip: Pagination offset (default 0)
Inputs: skip, limit, query, domain_id, +2 more.
enterprise_adminA
Query read-only BloodHound Enterprise administrative metadata.
info_type options:
self - get authenticated requester info
permissions - list permissions
permission - get a permission (needs: permission_id)
roles - list roles
role - get a role (needs: role_id)
users - list BloodHound users
users_minimal - list minimal user records
user - get a user (needs: user_id)
saml - list SAML providers
saml_sso - list SAML sign-on endpoints
saml_provider - get SAML provider (needs: saml_provider_id)
sso_providers - list SSO providers
sso_signing_certificate - get SSO signing certificate (needs: sso_provider_id)
Inputs: skip, limit, role_id, user_id, +4 more.
enterprise_infoA
Query read-only BloodHound Enterprise service information.
info_type options:
version - get API version metadata
spec - get the OpenAPI specification
audit - list audit logs
config - list application configuration parameters
features - list feature flags
args:
info_type: what to retrieve (default: version)
skip: audit pagination offset
limit: audit pagination limit
sort_by: optional audit sort field
status: optional audit status filter
Inputs: skip, limit, status, sort_by, +1 more.
entity_infoA
Query generic BHE entity endpoints not covered by a specific composite tool.
info_type options:
base_info - AD base entity info (needs: object_id)
base_controllables - controllable objects for a base entity (needs: object_id)
base_controllers - controllers of a base entity (needs: object_id)
container_info - container entity info (needs: object_id)
container_controllers - controllers of a container entity (needs: object_id)
azure_entity - generic Azure entity lookup by entity type (needs: entity_type)
args:
info_type: what to retrieve
object_id: AD object ID for base/container endpoints
entity_type: Azure entity type path segment
limit: max results for list endpoints
skip: pagination offset for list endpoints
Inputs: info_type (required), skip, limit, object_id, +1 more.
file_uploadA
Upload SharpHound/AzureHound collection files to BloodHound for ingest. Accepts .zip (SharpHound ZIP archive) or .json (individual collection file).
info_type options:
upload - full workflow for a single file: start -> upload -> end
(requires: file_path)
start_job - start a new upload job, returns job_id for multi-file uploads
upload_to_job - upload a file to an existing job (requires: job_id, file_path)
end_job - finalize an upload job and trigger ingest (requires: job_id)
list_jobs - list file upload jobs
completed_tasks - get completed tasks for an upload job (requires: job_id)
accepted_types - list accepted upload content types
Args:
info_type: operation to perform (default: upload)
file_path: absolute path to collection file (.zip or .json)
job_id: upload job ID (required for upload_to_job and end_job)
skip: pagination offset for list_jobs
limit: pagination limit for list_jobs
Inputs: skip, limit, job_id, file_path, +1 more.
gpo_infoA
Query GPO data from BloodHound. info_type options: info - general GPO properties and attributes computers - computers this GPO is applied to controllers - principals that can modify this GPO ous - OUs this GPO is linked to tier_zeros - tier-zero principals associated with this GPO users - users this GPO is applied to args: gpo_id: BloodHound object ID of the GPO (required) info_type: what to retrieve (default: info) limit: Max Results (default 100, useful in large environments) skip: Pagination offset (default 0)
Inputs: gpo_id (required), skip, limit, info_type.
graph_analysisA
Perform graph analysis operations in BloodHound
info_type options:
kinds - list graph node and edge kinds
search - search for nodes by name (needs: query; optional: search_type)
shortest_path - find shortest attack path between two nodes (needs: start_node, end_node; optional relationship_kinds)
edge_composition - decompose a complex edge into underlying relationships (needs: source_node, target_node, edge_type)
relay_targets - find valid NTLM relay targets for a given node (needs: source_node, target_node, edge_type)
pathfinding - get pathfinding result (optional: start_node, end_node, relationship_kinds)
acl_inheritance - get ACL inheritance path (needs: source_node, target_node)
args:
info_type: what type of graph operation to perform (required)
query: search text (for search)
search_type: type of search - fuzzy (default) or exact (for search)
start_node: Object ID of source node (for shortest_path)
end_node: Object ID of target node (for shortest_path)
source_node: Object ID of source node (for edge_composition and relay_targets)
target_node: Object ID of target node (for edge_composition and relay_targets)
edge_type: Realtionship type like "MemberOf", "AdminTo", (for edge_composition and relay_targets)
relationship_kinds: Comma-separated relationship filter (for shortest_path, optional)
Inputs: info_type (required), query, end_node, edge_type, +5 more.
group_infoA
Query group data from BloodHound. info_type options: info - general group properties and attributes admin_rights - machine/objects this group has admin rights on controllables - objects this group can control controllers - principals that have control over this group dcom_rights - machines this group can execute DCOM on members - users and groups that are members of this group memberships - groups this group belongs to (nested membership) ps_remote_rights - machines this group can PSRemote to rdp_rights - machines this group can RDP to sessions - machines this group has active sessions on args: group_id: BloodHound object ID of the group (required) info_type: what to retrieve (default: info) limit: Max Results (default 100, useful in large environments) skip: Pagination offset (default 0)
Inputs: group_id (required), skip, limit, info_type.
operations_infoA
Query read-only BloodHound Enterprise operational status and meta data.
info_type options:
datapipe_status - get datapipe status
analysis - get analysis request information
meta_nodes - get latest tier zero combo node for a domain (requires: domain_id)
meta_tree - get the meta tree graph for a domain (requires: domain_id)
meta_entity - get meta entity info (requires: object_id)
args:
info_type: what to retrieve (default: datapipe_status)
domain_id: domain ID for meta_nodes/meta_tree
object_id: object ID for meta_entity
Inputs: domain_id, info_type, object_id.
ou_infoA
Query OU data from BloodHound. info_type options: info - general OU Properties and attributes computers - computers in this OU groups - groups in this OU gpos - GPOs linked to this OU users - users in this OU args: ou_id: BloodHound object ID of the OU (required) info_type: what to retrieve (default: info) limit: Max Results (default 100, useful in large environments) skip: Pagination offset (default 0)
Inputs: ou_id (required), skip, limit, info_type.
risk_postureA
Query BloodHound Enterprise risk posture data.
info_type options:
stats - get current posture statistics
history - get posture history for a data type (needs: data_type)
args:
info_type: what to retrieve (default: stats)
data_type: posture history data type for history queries
Inputs: data_type, info_type.
user_infoA
Query user data from BloodHound info_type options: info - General user properties and attributes admin_rights - machine/objects this user has admin rights on constrained_delegation - services this use can delegate to via kerberos controllables - objects this use can control (WriteOwner, GenericAll, etc.) controllers - principals that have control over this user dcom_rights - machines this user can execute DCOM on memberships - groups this user belongs to ps_remote_rights - machines this user can PSRemote to rdp_rights - machines this user can RDP to sessions - machines this user has active sessions sql_admin_rights - SQL servers this user is admin on
Args:
user_id: BloodHound object ID of the user (required)
info_type: what to retrieve (default: info)
limit: Max Results (default 100, useful in large environments)
skip: Pagination offset (default 0)
Inputs: user_id (required), skip, limit, info_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 20 tools
Most tools target distinct entity types or domains (group, user, computer, domain, GPO, OU, ADCS, etc.), but there is some potential confusion between graph_analysis and cypher_query (both can explore paths) and between enterprise_info, operations_info, and collection_info which all deal with BHE system metadata. Descriptions are detailed enough to disambiguate in most cases.
Tool names are all snake_case and readable, but there is no consistent verb_noun pattern. Many use an '_info' suffix (group_info, user_info, computer_info), while others are noun phrases (asset_groups, attack_paths, cypher_query) or verb phrases (file_upload). This mix is acceptable but not a uniform convention.
20 tools is on the higher end but appropriate given the breadth of the BloodHound Enterprise API. Each tool covers a distinct functional area, and many pack multiple sub-operations via info_type, so the count is justified without being excessive.
The tool set covers major BloodHound domains: entity queries, graph analysis, cypher execution, attack paths, enterprise admin, file upload, collection status, and data quality. Minor gaps exist, such as limited Azure entity support and missing some niche BHE endpoints, but the surface is generally comprehensive for common workflows.
Maintenance
Related MCP Connectors
Deltabridge brings an AI-native cyber threat intelligence platform into your AI agent. Search a knowledge graph of 400,000+ threat actors, malware families, vulnerabilities, indicators and campaigns, mapped to MITRE ATT&CK. Look up and enrich IOCs, trace links between entities and read living briefs built from 300+ open sources. Read-only, scoped to your organisation, with OAuth sign-in or an API key. Included on Researcher, Business and Enterprise plans.
Authenticated LLM Agent (Bcrypt)
Connect LLM tools to your Algolia account with user-scoped access for internal workflows.
Related MCP Servers
- FlicenseCqualityDmaintenanceAn extension that allows Large Language Models to interact with and analyze Active Directory environments through natural language queries instead of manual Cypher queries.100165-
- AlicenseCqualityDmaintenanceEnables LLMs to perform Active Directory penetration testing using tools like NetExec, Bloodhound, Nmap, Certipy, and John the Ripper. Automates vulnerability discovery, attack path analysis, and documentation generation for security assessments.267MIT
- AlicenseBqualityDmaintenanceEnables security professionals to query and analyze Active Directory attack paths from BloodHound Community Edition data using natural language through Claude Desktop's Model Context Protocol interface.79143GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables natural language threat hunting and incident response by connecting LLMs to enterprise security data sources like Elasticsearch, EVTX logs, PCAP files, and Velociraptor.83 PyPI204GPL 3.0