Local MCP capabilities provider for Expo
Nothing to run from here
Mitre is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
3
downloads a day
local
runs on your machine
101
downloads in 30d
What it does
MCP server for MITRE ATT&CK knowledge base - technique lookup, threat intelligence, detection coverage analysis
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user mitre-mcp '--' npx -y mitre-mcp
# 2 — ask your agent for something these tools do
# mitre_campaign_profile, mitre_get_campaign, mitre_list_campaigns and 36 more
Mitre costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
LLAll 11 servers
lidless-labs11 servers
4 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Mitre as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user mitre-mcp '--' npx -y mitre-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
39 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Build a technique profile from observed techniques for campaign analysis and attribution
No parameter schema on file.
Get details on a known ATT&CK campaign including techniques, software, and attributed groups
No parameter schema on file.
List all known ATT&CK campaigns with names, dates, and brief descriptions
No parameter schema on file.
Search campaigns by keyword or by technique usage
No parameter schema on file.
Get details on a data source and its components with detectable techniques
No parameter schema on file.
Analyze detection coverage based on available data sources in your environment
No parameter schema on file.
Get details on a known threat group/APT including techniques and software used
No parameter schema on file.
Search threat groups by keyword or by technique usage
No parameter schema on file.
List all known threat groups with names, aliases, and brief descriptions
No parameter schema on file.
Force an update of the local ATT&CK data cache by re-downloading STIX bundles
No parameter schema on file.
Get current ATT&CK data version, freshness, and object counts
No parameter schema on file.
Map a security alert or observable to likely ATT&CK techniques with confidence scoring
No parameter schema on file.
Find technique overlap between threat groups for attribution assistance
No parameter schema on file.
Generate possible attack paths through the kill chain starting from a technique
No parameter schema on file.
Get details on a mitigation and all techniques it addresses
No parameter schema on file.
Get all mitigations applicable to a specific technique
No parameter schema on file.
Search mitigations by keyword
No parameter schema on file.
Generate an ATT&CK Navigator layer JSON for visualization. Supports coverage heatmaps, group technique overlays, campaign views, and custom technique highlighting.
No parameter schema on file.
Get details on a known software, malware, or tool including techniques and associated groups
No parameter schema on file.
Search software/malware by name, keyword, technique, or type
No parameter schema on file.
List all ATT&CK tactics in kill-chain order
No parameter schema on file.
Get details and all techniques under a specific tactic
No parameter schema on file.
Get full details of a specific ATT&CK technique by its ID (e.g., T1059, T1059.001)
No parameter schema on file.
Search ATT&CK techniques by keyword, tactic, platform, or data source
No parameter schema on file.
Map a MISP event
No parameter schema on file.
Search MISP for indicators (IOCs) related to specific ATT&CK techniques or threat groups
No parameter schema on file.
Create a MISP event pre-tagged with ATT&CK techniques and threat group galaxies
No parameter schema on file.
List recent MISP events with ATT&CK technique enrichment
No parameter schema on file.
Get connection status for all configured SOC integrations (Wazuh, TheHive, Cortex, MISP)
No parameter schema on file.
Cross-correlate ATT&CK techniques across Wazuh alerts, TheHive cases, and MISP events to find related activity
No parameter schema on file.
Map Cortex analyzers to ATT&CK data sources and calculate technique detection potential
No parameter schema on file.
Run Cortex analyzers on an observable and map results to ATT&CK context
No parameter schema on file.
Enrich TheHive case observables with ATT&CK context. Takes a case ID and adds ATT&CK technique tags, suggested mitigations, and threat group correlations.
No parameter schema on file.
Create a new TheHive case pre-populated with ATT&CK context from observed techniques
No parameter schema on file.
List TheHive cases with optional ATT&CK technique filtering
No parameter schema on file.
Get Wazuh manager status, agent summary, and rule statistics
No parameter schema on file.
Map a Wazuh alert (by rule ID, description, or groups) to ATT&CK techniques with confidence scoring
No parameter schema on file.
Analyze Wazuh rules and map them to ATT&CK technique coverage. Shows which techniques your Wazuh deployment can detect.
No parameter schema on file.
Fetch recent Wazuh alerts and enrich them with ATT&CK context
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Mitre or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 2.0.4 · scanned 13 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest82312e89215d9954e470e48b87ef36c777bfda61f9499db789bb673c3daca83c
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (39 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
4 of the 39 recovered tools are registered only when config.soc.wazuh holds (dist/cli.js:4951) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
3 of the 39 recovered tools are registered only when config.soc.thehive holds (dist/cli.js:4957) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
2 of the 39 recovered tools are registered only when config.soc.cortex holds (dist/cli.js:4963) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
4 of the 39 recovered tools are registered only when config.soc.misp holds (dist/cli.js:4969) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 26.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
26 tools are registered unconditionally · (1) 4 more only when config.soc.wazuh holds (dist/cli.js:4951) · (2) 3 more only when config.soc.thehive holds (dist/cli.js:4957) · (3) 2 more only when config.soc.cortex holds (dist/cli.js:4963) · (4) 4 more only when config.soc.misp holds (dist/cli.js:4969) — typically when a key or option is configured. All 39 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| mitre_get_technique | no tags | |
| mitre_search_techniques | no tags | |
| mitre_list_tactics | no tags | |
| mitre_get_tactic | no tags | |
| mitre_get_group | no tags | |
| mitre_search_groups | no tags | |
| mitre_list_groups | no tags | |
| mitre_get_software | no tags | |
| mitre_search_software | no tags | |
| mitre_get_mitigation | no tags | |
| mitre_mitigations_for_technique | no tags | |
| mitre_search_mitigations | no tags | |
| mitre_get_datasource | no tags | |
| mitre_detection_coverage | no tags | |
| mitre_map_alert_to_technique | no tags | |
| mitre_technique_overlap | no tags | |
| mitre_attack_path | no tags | |
| mitre_campaign_profile | no tags | |
| mitre_get_campaign | no tags | |
| mitre_list_campaigns | no tags | |
| mitre_search_campaigns | no tags | |
| mitre_navigator_layer | no tags | |
| mitre_update_data | no tags | |
| mitre_data_version | no tags | |
| mitre_wazuh_status conditional (1) | no tags | |
| mitre_map_wazuh_alert conditional (1) | no tags | |
| mitre_wazuh_rule_coverage conditional (1) | no tags | |
| mitre_wazuh_alerts conditional (1) | untrusted-input | untrusted-input: keyword "fetch" |
| mitre_thehive_enrich conditional (2) | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:3498, handler sends an HTTP PATCH (request("PATCH", …)) at dist/cli.js:3590 |
| mitre_thehive_create_case conditional (2) | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:3719 |
| mitre_thehive_list_cases conditional (2) | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:3829 |
| mitre_cortex_analyzer_coverage conditional (3) | no tags | |
| mitre_cortex_run_analyzers conditional (3) | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:4094 |
| mitre_misp_event_to_attack conditional (4) | no tags | |
| mitre_misp_search_indicators conditional (4) | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:4351 |
| mitre_misp_create_event conditional (4) | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:4462 |
| mitre_misp_list_events conditional (4) | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:4576 |
| mitre_soc_status | no tags | |
| mitre_cross_correlate | external-sink | external-sink: handler sends an HTTP POST (request("POST", …)) at dist/cli.js:4749 |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest82312e89215d9954
Scanned2026-10-13
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.0.4. Pin a release below and the command asks for exactly that one.
2.0.4
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Mitre can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.