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.
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
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
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.
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.
connectConnect to BloodHound CE and Neo4j. Overrides env var defaults for this session.
queryExecute an arbitrary Cypher query against the BloodHound Neo4j database.
standard_queryRun a named standard query from the built-in catalog.
list_queriesList available standard queries with descriptions. Optionally filter by category.
get_statusCheck connection status and return aggregate counts of clients, projects, and findings.
list_clientsList client organizations.
get_clientGet full details for a single client including associated projects.
list_projectsList projects/engagements.
get_projectGet full project details with associated findings, reports, and oplogs.
list_findingsList reported findings across engagements.
get_findingGet full finding details including CVSS, remediation, and evidence.
list_finding_templatesList the finding template library.
list_objectivesList project objectives and their sub-tasks.
list_targetsList target hosts and systems.
list_scopeList scope definitions (IP ranges, domains, etc.).
list_deconflictionsList deconfliction entries.
list_evidenceList evidence files.
list_whitecardsList white cards / exceptions.
list_observationsList observations/notes from reports.
list_reportsList reports.
get_infrastructureGet a summary of team servers and domains (combined view).
list_serversList team servers with checkout details.
list_domainsList registered domains with checkout details.
list_activity_logsList operation activity logs (oplog entries).
list_notesList notes for a given entity type (client, project, domain, or server).
searchSearch across clients, projects, findings, observations, and activity logs concurrently.
list_callbacksList Mythic callbacks (agents).
get_callbackGet full details for a single callback including payload and C2 profiles.
list_tasksList executed commands (tasks), most recent first.
get_task_outputGet decoded task output with optional line paging. Returns None if the task has no output.
list_credentialsList discovered credentials.
list_filesList downloaded/uploaded files.
get_file_contentsDownload a file to /tmp/mythic-readonly/ and return a preview plus the saved path.
list_artifactsList IOCs/artifacts generated by tasks.
list_keylogsList keylog captures.
list_screenshotsList screenshot metadata (use get_file_contents with agent_file_id to fetch image bytes).
list_processesList captured process listings.
list_file_browserBrowse captured file system data from agents.
list_tokensList Windows token captures.
interactSet the active implant for subsequent commands (ls, execute, upload, etc.).
get_sessionsList all active Sliver sessions (interactive real-time connections).
get_beaconsList all active Sliver beacons (async callback implants).
get_jobsList all active jobs (listeners) on the Sliver server.
start_mtls_listenerStart a mutual TLS (mTLS) C2 listener on the Sliver server.
start_https_listenerStart an HTTPS C2 listener on the Sliver server.
start_http_listenerStart an HTTP C2 listener on the Sliver server.
start_dns_listenerStart a DNS C2 listener on the Sliver server.
kill_jobKill an active listener job.
kill_sessionTerminate a Sliver session.
kill_beaconTerminate a Sliver beacon.
get_implant_buildsList all stored implant builds on the Sliver server.
regenerate_implantRegenerate a previously compiled implant by name. Returns the implant binary which can then be deployed to a target.
executeExecute a program on the target system.
lsList files and directories on the target system.
cdChange the implant's working directory.
pwdPrint the implant's current working directory.
mkdirCreate a directory on the target system.
rmRemove a file or directory on the target system.
uploadUpload a local file to the target system.
downloadDownload a file from the target and save it locally.
download_to_local_fileDownload a file from the target and save it to a local temporary file. Returns name and path.
psList running processes on the target.
terminate_processKill a process by PID on the target system.
ifconfigList network interfaces on the target.
netstatShow active network connections on the target.
screenshotCapture a screenshot of the target's display.
execute_assemblyExecute a .NET assembly in-memory on the target (execute-assembly).
execute_shellcodeInject and execute raw shellcode on the target.
sideloadLoad a shared library into a sacrificial process and call an export on the target.
get_envGet environment variables from the target system.
whoamiGet the current user context on the target system.
impersonateImpersonate a user on the target (Windows only).
make_tokenCreate a Windows logon token with the specified credentials.
revert_to_selfRevert any active impersonation back to the original user context.
run_asRun a process as a different user on the target.
get_systemAttempt to elevate to SYSTEM privileges on the target (Windows only).
process_dumpDump the memory of a process on the target (e.g. for LSASS credential extraction).
registry_readRead a value from the Windows registry on the target.
registry_writeWrite a value to the Windows registry on the target.
ghidra_statusReport which extra Ghidra features load in this PyGhidra runtime.
function_fid_hashCompute Ghidra FunctionID (FID) hashes for a function.
function_dataflowDecompiler dataflow summary for a function (HighFunction / P-code).
emulate_functionConcretely execute a function under Ghidra's emulator (Tier-3 repro).
diff_binariesDiff two project binaries at function granularity (#5 patch / variant diff).
diff_functionSide-by-side decompilation of one matched function pair from diff_binaries.
bsim_build_databaseBuild or extend a local BSim signature database from project binaries (#3 fuzzy).
bsim_query_functionQuery one function against a BSim database for similar functions (Tier-1 fuzzy ID, #3).
bsim_overviewBest BSim match for every function in a binary — the annotation-queue denoiser (#3).
inventory_statusProbe whether the underlying CLIs and scripts this MCP relies on are reachable on this host.
run_corpus_inventoryRun a parallel, resumable first-pass inventory over an APK corpus.
extract_componentsEmit 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_componentsApply risk priors to each component row and emit a ranked inbox.
detect_runtime_kindClassify an APK's runtime in one second using `unzip -l` only.
detect_protectorDetect commercial Android protectors (DexProtector, Promon Shield) and recommend a triage strategy.
dexprotector_unpackStatic-unpack DexProtector's libdp.so without an Android device.
extract_api_mapRegex-extract API endpoints, generated clients, request-signing hints, feature flags, object IDs, and workflow verbs from decompiled APK sources.
rank_backend_richnessSort backend_richness summaries by score and emit an operator inbox.
normalize_semantic_findingsNormalize, deduplicate, and render Android semantic finding hypotheses.
bbot_healthCheck BBOT and Neo4j connectivity.
run_bbot_scanExecute a BBOT reconnaissance scan.
216 further tools are not listed here. The complete surface is in the source.
CAIDO_PATCAIDO_PROXYCAIDO_URLBLOODHOUND_URLBLOODHOUND_USERNAMEBLOODHOUND_PASSWORDNEO4J_URLNEO4J_USERNAMENEO4J_PASSWORDNEO4J_DATABASEGHOSTWRITER_URLGHOSTWRITER_API_TOKENGHOSTWRITER_USERNAMEGHOSTWRITER_PASSWORDMYTHIC_PASSWORDMYTHIC_API_TOKENSLIVER_TIMEOUTSLIVER_CONFIG_FILECAPABILITY_FLAG__MYTHIC_C2__TASKINGCAPABILITY_FLAG__MYTHIC_C2__APOLLOBINANAL_CACHE_ROOTANDROID_RESEARCH_MAX_OUTPUT_CHARSANDROID_RESEARCH_TIMEOUTNEO4J_URINEO4J_USERBBOT_DATA_DIRSHODAN_API_KEYSHODAN_API_URLPE_TRIAGE_MAX_OUTPUT_CHARSPE_TRIAGE_TIMEOUTCAPA_RULESCAPA_SIGNATURESYARA_RULESMVT_MAX_OUTPUT_CHARSMVT_TIMEOUTMVT_COMMANDVOLATILITY_MAX_OUTPUT_CHARSVOLATILITY_TIMEOUTVOLATILITY_COMMANDAGENT_BROWSER_MAX_OUTPUT_CHARSAGENT_BROWSER_TIMEOUTAGENT_BROWSER_COMMANDCAIDO_TOKEN_PATHGITHUB_API_URLGITHUB_TOKENH1_USERNAMEH1_API_TOKENJIRA_BASE_URLJIRA_EMAILJIRA_API_TOKENJXSCOUT_BINARYLINEAR_API_URLLINEAR_ACCESS_TOKENLINEAR_API_KEYPROTOSCOPE_MAX_OUTPUT_CHARSPROTOSCOPE_TIMEOUTPROTOSCOPE_COMMANDSECURITYCONTEXT_API_KEYTHERMOPTIC_PROXY_URLAIRT_ASSESSMENT_PATHAIRT_ENV_TEARDOWN_GRACE_SECAIRT_ENV_REGISTRY_PATHAIRT_WORKFLOWS_DIRDREADNODE_RUNTIME_TOKENASM_WORKER_MODELDREADNODE_RUNTIME_URLCAPABILITY_PORTPYTHONPATHDREADNODE_SKIP_AUTO_INSTALLSECURE_SOFTWARE_DIRSPECTRA_ASSURE_TOKENSPECTRA_ASSURE_HOSTSPECTRA_ASSURE_PATHSPECTRA_ASSURE_ORGSPECTRA_ASSURE_GROUPINTERACTSH_SERVERCF_ACCOUNT_IDCF_API_TOKENCLOUDFLARE_API_TOKENCLOUDFLARE_ACCOUNT_IDDREADNODE_ORGANIZATIONDREADNODE_WORKSPACEDREADNODE_PROJECTDREADNODE_SERVERDREADNODE_LLM_BASEDREADNODE_LLM_API_KEYTARGET_API_KEYANDROZOO_API_KEYBHE_VERIFY_SSLBHE_TIMEOUTBHE_TOKEN_IDBHE_TOKEN_KEYBHE_JWTBHE_USERNAMEBHE_PASSWORDDOTNET_ROOTDOTNET_TOOLS_LIB_DIRDREADNODE_CAPABILITIES_DIRMYTHIC_DATA_DIRCAPABILITY_FLAG__MYTHIC_C2__TRIAGEDREADNODE_ORGDREADNODE_API_KEYMYTHIC_SERVER_IPMYTHIC_SERVER_PORTMYTHIC_USERNAMEMYTHIC_TIMEOUTTool 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.
[](https://m8ven.ai/mcp/dreadnode/capabilities)?variant=verified from the URL.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