capabilities (dreadnode/capabilities) is an MCP server listed on the M8ven Trust Index. It scores 60 out of 100, grade C. It declares 319 tools. No publisher has claimed this listing.

C
Caution
60/100

capabilities

Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

dreadnode

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — build_media_manifest (line 1104: result = subprocess.run()
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 23 credentials: BLOODHOUND_PASSWORD, NEO4J_PASSWORD, GHOSTWRITER_API_TOKEN, GHOSTWRITER_PASSWORD, MYTHIC_PASSWORD, MYTHIC_API_TOKEN, SHODAN_API_KEY, GITHUB_TOKEN, H1_API_TOKEN, JIRA_API_TOKEN, LINEAR_ACCESS_TOKEN, LINEAR_API_KEY, SECURITYCONTEXT_API_KEY, DREADNODE_RUNTIME_TOKEN, SPECTRA_ASSURE_TOKEN, CF_API_TOKEN, CLOUDFLARE_API_TOKEN, DREADNODE_LLM_API_KEY, TARGET_API_KEY, ANDROZOO_API_KEY, BHE_TOKEN_KEY, BHE_PASSWORD, DREADNODE_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes316 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

connect

Connect to BloodHound CE and Neo4j. Overrides env var defaults for this session.

query

Execute an arbitrary Cypher query against the BloodHound Neo4j database.

standard_query

Run a named standard query from the built-in catalog.

list_queries

List available standard queries with descriptions. Optionally filter by category.

get_status

Check connection status and return aggregate counts of clients, projects, and findings.

list_clients

List client organizations.

get_client

Get full details for a single client including associated projects.

list_projects

List projects/engagements.

get_project

Get full project details with associated findings, reports, and oplogs.

list_findings

List reported findings across engagements.

get_finding

Get full finding details including CVSS, remediation, and evidence.

list_finding_templates

List the finding template library.

list_objectives

List project objectives and their sub-tasks.

list_targets

List target hosts and systems.

list_scope

List scope definitions (IP ranges, domains, etc.).

list_deconflictions

List deconfliction entries.

list_evidence

List evidence files.

list_whitecards

List white cards / exceptions.

list_observations

List observations/notes from reports.

list_reports

List reports.

get_infrastructure

Get a summary of team servers and domains (combined view).

list_servers

List team servers with checkout details.

list_domains

List registered domains with checkout details.

list_activity_logs

List operation activity logs (oplog entries).

list_notes

List notes for a given entity type (client, project, domain, or server).

search

Search across clients, projects, findings, observations, and activity logs concurrently.

list_callbacks

List Mythic callbacks (agents).

get_callback

Get full details for a single callback including payload and C2 profiles.

list_tasks

List executed commands (tasks), most recent first.

get_task_output

Get decoded task output with optional line paging. Returns None if the task has no output.

list_credentials

List discovered credentials.

list_files

List downloaded/uploaded files.

get_file_contents

Download a file to /tmp/mythic-readonly/ and return a preview plus the saved path.

list_artifacts

List IOCs/artifacts generated by tasks.

list_keylogs

List keylog captures.

list_screenshots

List screenshot metadata (use get_file_contents with agent_file_id to fetch image bytes).

list_processes

List captured process listings.

list_file_browser

Browse captured file system data from agents.

list_tokens

List Windows token captures.

interact

Set the active implant for subsequent commands (ls, execute, upload, etc.).

get_sessions

List all active Sliver sessions (interactive real-time connections).

get_beacons

List all active Sliver beacons (async callback implants).

get_jobs

List all active jobs (listeners) on the Sliver server.

start_mtls_listener

Start a mutual TLS (mTLS) C2 listener on the Sliver server.

start_https_listener

Start an HTTPS C2 listener on the Sliver server.

start_http_listener

Start an HTTP C2 listener on the Sliver server.

start_dns_listener

Start a DNS C2 listener on the Sliver server.

kill_job

Kill an active listener job.

kill_session

Terminate a Sliver session.

kill_beacon

Terminate a Sliver beacon.

get_implant_builds

List all stored implant builds on the Sliver server.

regenerate_implant

Regenerate a previously compiled implant by name. Returns the implant binary which can then be deployed to a target.

execute

Execute a program on the target system.

ls

List files and directories on the target system.

cd

Change the implant's working directory.

pwd

Print the implant's current working directory.

mkdir

Create a directory on the target system.

rm

Remove a file or directory on the target system.

upload

Upload a local file to the target system.

download

Download a file from the target and save it locally.

download_to_local_file

Download a file from the target and save it to a local temporary file. Returns name and path.

ps

List running processes on the target.

terminate_process

Kill a process by PID on the target system.

ifconfig

List network interfaces on the target.

netstat

Show active network connections on the target.

screenshot

Capture a screenshot of the target's display.

execute_assembly

Execute a .NET assembly in-memory on the target (execute-assembly).

execute_shellcode

Inject and execute raw shellcode on the target.

sideload

Load a shared library into a sacrificial process and call an export on the target.

get_env

Get environment variables from the target system.

whoami

Get the current user context on the target system.

impersonate

Impersonate a user on the target (Windows only).

make_token

Create a Windows logon token with the specified credentials.

revert_to_self

Revert any active impersonation back to the original user context.

run_as

Run a process as a different user on the target.

get_system

Attempt to elevate to SYSTEM privileges on the target (Windows only).

process_dump

Dump the memory of a process on the target (e.g. for LSASS credential extraction).

registry_read

Read a value from the Windows registry on the target.

registry_write

Write a value to the Windows registry on the target.

ghidra_status

Report which extra Ghidra features load in this PyGhidra runtime.

function_fid_hash

Compute Ghidra FunctionID (FID) hashes for a function.

function_dataflow

Decompiler dataflow summary for a function (HighFunction / P-code).

emulate_function

Concretely execute a function under Ghidra's emulator (Tier-3 repro).

diff_binaries

Diff two project binaries at function granularity (#5 patch / variant diff).

diff_function

Side-by-side decompilation of one matched function pair from diff_binaries.

bsim_build_database

Build or extend a local BSim signature database from project binaries (#3 fuzzy).

bsim_query_function

Query one function against a BSim database for similar functions (Tier-1 fuzzy ID, #3).

bsim_overview

Best BSim match for every function in a binary — the annotation-queue denoiser (#3).

inventory_status

Probe whether the underlying CLIs and scripts this MCP relies on are reachable on this host.

run_corpus_inventory

Run a parallel, resumable first-pass inventory over an APK corpus.

extract_components

Emit one JSONL row per (apk, component) by streaming every `androguard.json` under the inventory directory, falling back to `aapt2 dump xmltree` for APKs where Androguard errored.

rank_components

Apply risk priors to each component row and emit a ranked inbox.

detect_runtime_kind

Classify an APK's runtime in one second using `unzip -l` only.

detect_protector

Detect commercial Android protectors (DexProtector, Promon Shield) and recommend a triage strategy.

dexprotector_unpack

Static-unpack DexProtector's libdp.so without an Android device.

extract_api_map

Regex-extract API endpoints, generated clients, request-signing hints, feature flags, object IDs, and workflow verbs from decompiled APK sources.

rank_backend_richness

Sort backend_richness summaries by score and emit an operator inbox.

normalize_semantic_findings

Normalize, deduplicate, and render Android semantic finding hypotheses.

bbot_health

Check BBOT and Neo4j connectivity.

run_bbot_scan

Execute a BBOT reconnaissance scan.

216 further tools are not listed here. The complete surface is in the source.

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCAIDO_PAT
configCAIDO_PROXY
configCAIDO_URL
configBLOODHOUND_URL
configBLOODHOUND_USERNAME
🔐 secretBLOODHOUND_PASSWORD
configNEO4J_URL
configNEO4J_USERNAME
🔐 secretNEO4J_PASSWORD
configNEO4J_DATABASE
configGHOSTWRITER_URL
🔐 secretGHOSTWRITER_API_TOKEN
configGHOSTWRITER_USERNAME
🔐 secretGHOSTWRITER_PASSWORD
🔐 secretMYTHIC_PASSWORD
🔐 secretMYTHIC_API_TOKEN
configSLIVER_TIMEOUT
configSLIVER_CONFIG_FILE
configCAPABILITY_FLAG__MYTHIC_C2__TASKING
configCAPABILITY_FLAG__MYTHIC_C2__APOLLO
configBINANAL_CACHE_ROOT
configANDROID_RESEARCH_MAX_OUTPUT_CHARS
configANDROID_RESEARCH_TIMEOUT
configNEO4J_URI
configNEO4J_USER
configBBOT_DATA_DIR
🔐 secretSHODAN_API_KEY
configSHODAN_API_URL
configPE_TRIAGE_MAX_OUTPUT_CHARS
configPE_TRIAGE_TIMEOUT
configCAPA_RULES
configCAPA_SIGNATURES
configYARA_RULES
configMVT_MAX_OUTPUT_CHARS
configMVT_TIMEOUT
configMVT_COMMAND
configVOLATILITY_MAX_OUTPUT_CHARS
configVOLATILITY_TIMEOUT
configVOLATILITY_COMMAND
configAGENT_BROWSER_MAX_OUTPUT_CHARS
configAGENT_BROWSER_TIMEOUT
configAGENT_BROWSER_COMMAND
configCAIDO_TOKEN_PATH
configGITHUB_API_URL
🔐 secretGITHUB_TOKEN
configH1_USERNAME
🔐 secretH1_API_TOKEN
configJIRA_BASE_URL
configJIRA_EMAIL
🔐 secretJIRA_API_TOKEN
configJXSCOUT_BINARY
configLINEAR_API_URL
🔐 secretLINEAR_ACCESS_TOKEN
🔐 secretLINEAR_API_KEY
configPROTOSCOPE_MAX_OUTPUT_CHARS
configPROTOSCOPE_TIMEOUT
configPROTOSCOPE_COMMAND
🔐 secretSECURITYCONTEXT_API_KEY
configTHERMOPTIC_PROXY_URL
configAIRT_ASSESSMENT_PATH
configAIRT_ENV_TEARDOWN_GRACE_SEC
configAIRT_ENV_REGISTRY_PATH
configAIRT_WORKFLOWS_DIR
🔐 secretDREADNODE_RUNTIME_TOKEN
configASM_WORKER_MODEL
configDREADNODE_RUNTIME_URL
configCAPABILITY_PORT
configPYTHONPATH
configDREADNODE_SKIP_AUTO_INSTALL
configSECURE_SOFTWARE_DIR
🔐 secretSPECTRA_ASSURE_TOKEN
configSPECTRA_ASSURE_HOST
configSPECTRA_ASSURE_PATH
configSPECTRA_ASSURE_ORG
configSPECTRA_ASSURE_GROUP
configINTERACTSH_SERVER
configCF_ACCOUNT_ID
🔐 secretCF_API_TOKEN
🔐 secretCLOUDFLARE_API_TOKEN
configCLOUDFLARE_ACCOUNT_ID
configDREADNODE_ORGANIZATION
configDREADNODE_WORKSPACE
configDREADNODE_PROJECT
configDREADNODE_SERVER
configDREADNODE_LLM_BASE
🔐 secretDREADNODE_LLM_API_KEY
🔐 secretTARGET_API_KEY
🔐 secretANDROZOO_API_KEY
configBHE_VERIFY_SSL
configBHE_TIMEOUT
configBHE_TOKEN_ID
🔐 secretBHE_TOKEN_KEY
configBHE_JWT
configBHE_USERNAME
🔐 secretBHE_PASSWORD
configDOTNET_ROOT
configDOTNET_TOOLS_LIB_DIR
configDREADNODE_CAPABILITIES_DIR
configMYTHIC_DATA_DIR
configCAPABILITY_FLAG__MYTHIC_C2__TRIAGE
configDREADNODE_ORG
🔐 secretDREADNODE_API_KEY
configMYTHIC_SERVER_IP
configMYTHIC_SERVER_PORT
configMYTHIC_USERNAME
configMYTHIC_TIMEOUT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

319/319 tools missing one or more hints — connect (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); query (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); standard_query (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +316 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

5 tools perform destructive updates without destructiveHint — volatility_yara_scan deletes at line 470 (Path(rules_path).unlink(missing_ok=True)); fix_workflow_errors deletes at line 445 (shutil.rmtree(cache_dir)); clear_session_context deletes at line 164 (SESSION_PATH.unlink())

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — build_media_manifest (line 1104: result = subprocess.run()

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool test coverage

223/319 tools referenced in tests (70%)

Write tests that reference each tool by name so every tool has at least one test.

Tool description accuracy

screenshot: description implies read-only but handler writes/deletes/executes; build_media_manifest: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/dreadnode/capabilities?variant=verified)](https://m8ven.ai/mcp/dreadnode/capabilities)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: a8d2002bfcb797dc79f38c04597331d812b9b07f
code hash: ddb23266278c87aa934a2524875effa90cb101e35e0b4f1819928eeac18e0c7c
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client