Mallory
Server Details
Queries IOCs, vulnerabilities, threat actors and malware correlated from thousands of sources, retaining source-attributed evidence. Collection spans feeds, reports and advisories, social and dark-web monitoring, and Mallory's own sandboxing and internet scanning; a free community tier is available with an account and API key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 38 tools
Most tools are clean get/list/update/create pairs for distinct entity types, and descriptions explicitly direct agents to the named tools before queryApi. The main ambiguity is that listVulnerabilities and searchVulnerabilities read as near-duplicates, while queryApi can re-express many named tools, so a few selections require care.
All tool names use a predictable camelCase verb+entity construction, such as getAsset, listFindings, createFinding, bulkUpdateFindings, and linkFindingTicket. queryApi is the only generic name, but it appropriately signals the single escape-hatch tool.
At 38 tools this is well above the 25-tool threshold, with many parallel get/list pairs across roughly fifteen intelligence entity types. Each pair is defensible on a broad CTI platform, but the total surface is heavy for an MCP server and increases selection cost.
Findings have create/read/update/bulk-update and ticket-link lifecycle coverage, while the main intelligence entities have get/list tools and queryApi covers relationship pivots, asset subresources, and missing domains. Gaps are minor: no finding deletion by design, no direct asset mutation, and schedule management is explicitly absent.
Publisher details
- Operator
- Mallory · Publisher source
- Operator website
- https://mallory.ai · Publisher source
- Vendor relationship
- Not applicable
- Documentation
- https://docs.mallory.ai/integrations/mallory-mcp · Publisher source
- Privacy policy
- Not provided
- Trust center
- https://trust.mallory.ai · Publisher source
- Restrictions
- No setup restrictions
Available Tools
38 toolsbulkUpdateFindingsAInspect
Change the status and/or severity of a SET of findings in the caller's own organization, selected either by filter or by an explicit list of uuids. Use it for "dismiss all the unrotated-secret findings", "mark everything on foo/bar medium". For ONE finding you already hold a uuid for, use updateFinding instead; this tool is for sets you can only describe.
READ THIS BEFORE CALLING — IT WRITES THE MOMENT IT IS CALLED. There is no dry run, no preview mode and no confirmation step inside this tool, and no single call that puts back what it changed. The check has to happen BEFORE the call, in conversation with the user:
Work out the selection, and resolve it yourself with listFindings using the SAME filters.
Show the user what it covers — the count, and the findings themselves (name them if there are only a few).
Say in one sentence what will change and how many findings it affects.
Get a plain yes. Then call this ONCE. Never call this tool to find out what would match: listFindings and queryApi answer that and write nothing. Never call it on your own initiative, and never as a tidy-up you decided on yourself.
SCOPE is required and has no default. Over MCP it must be "tenant" — every finding in the organization, including ones filed months ago by people who are not in this conversation. "this_thread" only means anything inside the Mallory chat app, which is the only place a conversation thread exists; here it can only fail with MISSING_THREAD. If you do get MISSING_THREAD, do not "fix" it by re-sending with "tenant": that is a far larger write than the one that just failed, and the user has not agreed to it.
SELECTING
Pass
filtersoruuids, never both, and never invent a uuid — use only uuids a previous tool result actually returned (at most 500).A tenant selection needs at least one filter, or a uuid list — there is no "everything we have" call. A selection filtered ONLY by status and/or severity still covers essentially the whole organization; the result flags that as
broad, and you must say so explicitly when you report back.A phrase like "the unrotated-secret findings" names a problem TYPE, not an asset: find the definition first with queryApi, path "/v1/finding_definitions" (slug__contains / title__contains), then filter on definition_slug, or definition_slug__in when several definitions match the phrase. definition_category is a whole category and much broader than a slug — confirm before using it.
An asset is
asset_identifier(e.g. "foo/bar" for a GitHub repo). Try the exact value first and fall back to asset_identifier__contains only if it matched nothing.Add
status: "open"unless the user said otherwise: re-dismissing already-dismissed findings is churn they did not ask for.searchis fuzzy full text over title, asset_identifier, body, summary, remediation and asset_details — the only way to reach a cloud account id, region or owner, none of which are filterable columns. It is also the easiest way to hit findings the user did not mean, so withsearchespecially, show them the listFindings result before you call.
BOUNDS AND REFUSALS — each is an answer, not an obstacle to route around:
TOO_MANY_MATCHES: the selection is over the 500-finding limit for one update. Narrow it (a definition_slug, a category, an asset filter, a created_at range). Do NOT page through it, and do NOT split it into several calls to get under the limit — each call is its own write, and the user agreed to one change rather than to a sequence of them.
NO_MATCHES: nothing matched, or everything matched already holds the value you are setting. When you set ONE field on a
filtersselection, findings already at that value are excluded from the selection, so the count you get back is the real blast radius and repeating the call for the same request is inert. Setting status AND severity together drops that exclusion — the selector cannot express "not both at once" — so there the count can include findings that were already correct, and a repeat call writes them all again. Auuidsselection is never narrowed that way — the uuid list IS the selection — so a repeat call there rewrites every finding you named. Never re-issue a call to find out whether the first one landed: the result told you. Tell the user there was nothing to change and stop. Do NOT loosen the filters and retry until something matches: a selection that only appeared after you widened it is not the one the user described.PLAN_LIMIT / FORBIDDEN: nothing was written and nothing is broken. Say so plainly and do not retry.
In user-facing status messages, use "fixed" and "mark as fixed" consistently.
ENUM VALUES ARE CASE-SENSITIVE AND EACH FIELD HAS ITS OWN SET. severity is UPPERCASE (CRITICAL, HIGH, MEDIUM, LOW, INFO). status is lowercase with exactly three values: open, fixed, dismissed — "resolved", "closed" and "assigned" are not statuses. The resolution reasons (false_positive, accepted_risk, not_applicable, duplicate, fixed_externally, other) are a SEPARATE field that this tool cannot set: false_positive is not a status. definition_category is lowercase-hyphenated.
WHAT IT CANNOT DO: title, summary, body, remediation, confidence and qualifier — those are updateFinding, one finding at a time, because they are per-asset prose or part of core's dedupe key. resolution_reason is settable by NEITHER tool: it is recorded in the Mallory UI when someone closes a finding there, so listFindings can read and filter on it but nothing here writes it. It cannot create findings (createFinding). Setting status back to "open" is allowed but unusual; reopening two findings onto the same asset trips core's open-finding uniqueness constraint and rolls the whole batch back, so do not retry that — reopen one at a time.
Inputs: set (required), scope (required), uuids, filters.
createFindingAInspect
Create one or more findings in Mallory. A finding is a durable record of a security problem or an evidenced observation, such as product presence, on a specific asset. Product presence alone does not establish a vulnerability or require removal or patching. The asset must belong to the caller's own organization. A finding is not a chat message or a note to yourself. It is visible in the Mallory UI to everyone in that organization, and nothing on this server deletes one: a finding filed by mistake can only be marked dismissed with updateFinding.
WRITES IMMEDIATELY. There is no draft, no preview and no confirmation step — calling this tool IS the write. Only call it when the user has asked, in so many words, for findings to be filed in Mallory ("create a finding for that", "file these"). Finishing an investigation is not permission to file its results: report them and let the user decide.
WHAT TO SEND
definition_slug must ALREADY EXIST in the catalog. Look one up with the queryApi tool, path "/v1/finding_definitions" (filter by category or severity to narrow). Never invent a slug, and never substitute a near-match for one that was rejected — that files the wrong kind of finding.
One finding per condition per asset. Five misconfigured buckets are five findings sharing a definition_slug with five different asset_identifier values, not one finding listing five buckets. When one asset has several instances of the same definition, use a distinct qualifier for each instance, such as the detected product name, IAM role, or workflow file. Keep each qualifier byte-identical across runs: it is part of the duplicate key. Without distinct qualifiers, separate instances can be reported as DUPLICATE. Send the whole batch in ONE call (max 25): each is created independently, so one duplicate does not block the rest.
asset_type is a provider.service.object value (e.g. aws.s3.bucket, aws.iam.role, github.repo, azure.storage.account), or "generic" when nothing fits. Legacy underscore forms like "s3_bucket" are rejected.
Keep asset_type and asset_identifier byte-identical across runs as the duplicate key and add asset_uuid as a link to a resolved asset of any class. Find a name (or part of one) with GET /v1/assets using where=display_name == "" or display_name.contains(""); this searches every class and needs no class or key type. For an identity key whose kind the user provides (serial number, ARN, repo URL, digest), use GET /v1/assets/by-identifier?type=&value=; type is the identity key type, not the asset class, and class is optional. Count distinct asset_uuid values across the complete result: while there is a next_cursor, read the next page with cursor and unchanged filters and sort. A truncated or incomplete lookup cannot produce a link; with zero or multiple matches, omit asset_uuid and never guess. Keep the same pair whether or not resolution succeeds. For new github.repo findings use github.com/owner/repo; never rewrite an existing identifier. Send asset_uuid without a pair only when the resolved asset itself is the finding identity. Never send asset_type "host" or "asset". A partial pair, or neither a pair nor asset_uuid, is INVALID. ASSET_NOT_FOUND means the UUID is not an asset of this tenant. Link the returned canonical asset_uuid as /environment/{asset_uuid}.
summary / body / remediation are markdown, and are read by people who were not in your conversation: what you observed, how you established it, and appropriate next steps. For a product-presence observation, next steps may be ownership or expected-use review; do not invent a security problem or fix.
evidence is one entry per thing you actually OBSERVED — the query and what it returned, the endpoint and its status, the file and the matching line. Three observations are three entries. Never write evidence for something you inferred rather than observed; lower confidence and say so in body instead.
ENUM VALUES ARE CASE-SENSITIVE AND EACH FIELD HAS ITS OWN SET. severity is UPPERCASE (CRITICAL, HIGH, MEDIUM, LOW, INFO) and optional — omit it and the definition's own default applies, which is usually right; override only when this instance is genuinely worse or milder than the type normally is, and say why in body. confidence is lowercase (low, medium, high). Status is not settable here: a finding is created open, and status values are lowercase (see updateFinding).
OUTCOMES come back per finding, in created and failed:
DUPLICATE — an open finding already covers that asset (for asset_uuid without a pair, that asset or an asset merged into it), and
existing_finding_uuidnames it. Say so and move on. Do NOT re-word the title and retry; to change the one that exists, call updateFinding with that uuid.UNKNOWN_DEFINITION — the slug is not in the catalog. Look up a real one; do not guess a neighbouring slug.
INVALID — core rejected a field, most often asset_type. Fix that field, not the slug.
ASSET_NOT_FOUND — asset_uuid is not an asset of this organization. Nothing was written. Resolve it again; never guess a UUID or change the asset pair.
INVALID_ASSET_IDENTIFIER — asset_identifier names no asset (a placeholder such as "unknown", or a bare word such as a tool or data-source name, with asset_type "generic"). Nothing was written. Use the real affected asset from the source data (host:port, hostname, URL, account, repository); never invent one.
PLAN_LIMIT — findings are not included in this tenant's plan. The request was fine, nothing is broken and nothing was written: tell the user, pass on the upgrade link if the outcome carries one, and do not retry or reach for another tool to file it.
A created finding carries the canonical linked asset_uuid; an absent link is null.
list_url is null outside the Mallory chat app — there is no conversation for an MCP call to scope a list to. Read a created finding back with getFinding using the uuid in created, or browse the tenant's findings with listFindings.
Inputs: findings (required).
findAffectedProductsAInspect
Find technology products and software affected by a specific vulnerability. Provide either a CVE ID (e.g., CVE-2024-1234) or a vulnerability UUID. If you do not have a CVE ID, first use the vulnerability search tool. Returns a list of affected products with organization information and version details. Use this to understand the scope and impact of a vulnerability.
Inputs: vulnerability_id (required).
getAdvisoryAInspect
Fetch a single Mallory advisory by identifier (an advisory UUID) and return its full detail. Returns: advisory title/identifier, source/vendor, severity, affected products and vulnerabilities, and published date. If you only have a name or search terms, call listAdvisories first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getAssetAInspect
Fetch the full detail of one asset in your organization's own inventory by asset_uuid, returning core's object unchanged. A merged UUID resolves: the response then carries requested_uuid, merged_from, current and source_records. Find asset_uuid values with listAssets. For an asset's products, packages, vulnerabilities, lookup by identifier, and timelines, use queryApi (/v1/assets/{asset_uuid}/products, /packages, /vulnerabilities, /v1/assets/by-identifier).
Inputs: asset_uuid (required).
getAttackPatternAInspect
Fetch a single Mallory attack pattern by identifier (a MITRE ATT&CK ID (e.g. T1566), a UUID, or the technique name) and return its full detail. Returns: mitre_id, name, description, tactic(s), and associated threat actors and malware. If you only have a name or search terms, call listAttackPatterns first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getBreachAInspect
Fetch a single Mallory breach by identifier (a UUID or the breach internal_name) and return its full detail. Returns: name, description, affected organizations, record_type and loss_type, affected record counts, associated threat actors/malware/attack-patterns, and dates. If you only have a name or search terms, call listBreaches first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getExploitAInspect
Fetch a single Mallory exploit by identifier (a UUID or a CVE ID) and return its full detail. Returns: title/name, description, source and maturity, and the vulnerabilities (CVEs) it targets. If you only have a name or search terms, call listExploits first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getFindingAInspect
Fetch a single Mallory finding by identifier (a UUID (nothing else resolves)) and return its full detail. Returns: title, status, severity, confidence, the owning definition's slug/title/category, asset type and identifier, resolution_reason, the thread_uuid of the investigation that produced it, and timestamps; the detail object adds body / summary / remediation / evidence, any linked external tickets, and entities — the threat actors, vulnerabilities and stories this finding resolved to, which is the pivot back into Mallory's intel graph. If you only have a name or search terms, call listFindings first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getMalwareAInspect
Fetch a single Mallory malware by identifier (a UUID or the malware family name (e.g. Cobalt Strike)) and return its full detail. Returns: name/display_name plus aliases, description, capabilities, family, associated threat actors and ATT&CK techniques, related vulnerabilities, and trending activity. If you only have a name or search terms, call listMalware first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getObservableAInspect
Fetch a single Mallory observable (IOC) — an IP, domain, URL, email address, or file hash — with its reputation/opinion data. Identify it EITHER by uuid, OR by the (type, name) pair: e.g. type='domain' name='evil.example.com'; type='ip.v4' name='1.2.3.4'; type='hash.sha256' name=''. Returns the observable's type, value, verdict/opinion summary, and linked references. To filter/search observables use listObservables; to get the IOCs Mallory extracted from a specific report use referenceObservables.
Inputs: name, type, uuid.
getOrganizationAInspect
Fetch a single Mallory organization by identifier (a UUID or the organization name) and return its full detail. Returns: name, description, associated products and breaches, and mention activity. If you only have a name or search terms, call listOrganizations first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getProductAInspect
Fetch a single Mallory product by identifier (a product UUID) and return its full detail. Returns: vendor and product name, CPE, description, and links to advisories and vulnerabilities. If you only have a name or search terms, call listProducts first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getReferenceAInspect
Look up a Mallory reference — a source document (article, report, advisory, blog post, or social post) that Mallory ingested and analyzed. Two modes: (1) pass reference with a UUID, url_hash, or a pasted Mallory reference URL to fetch that exact reference; (2) pass urlFilter with a substring of the source's web URL (or its slug) to resolve which reference Mallory has for an article when you only have its web address. Returns reference metadata (source, title/topic, published date, URL). To then pull the IOCs/observables Mallory extracted from a reference, call referenceObservables with the reference's UUID.
Inputs: limit, reference, urlFilter.
getSoftwareExtensionAInspect
Fetch a single Mallory software extension by identifier (an extension UUID) and return its full detail. Returns: extension name, marketplace/ecosystem, publisher, install count, description, and known configurations. If you only have a name or search terms, call listSoftwareExtensions first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getSoftwarePackageAInspect
Fetch a single Mallory software package by identifier (a package UUID) and return its full detail. Returns: package name, ecosystem, description, known configurations, supply-chain compromise evidence, and upstream OpenSSF Scorecard assessment (0–10, higher is better). If you only have a name or search terms, call listSoftwarePackages first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getThreatActorAInspect
Fetch a single Mallory threat actor by identifier (a UUID or the actor's name (e.g. APT29, Lazarus Group)) and return its full detail. Returns: canonical name/display_name plus aliases, description, motivation, sponsor, family, targeted industries and source/target geographies, and trending activity. If you only have a name or search terms, call listThreatActors first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
getVulnerabilityAInspect
Fetch a single Mallory vulnerability by identifier (a CVE ID (e.g. CVE-2024-1234) or a UUID) and return its full detail. Returns: cve_id, description, CVSS (cvss_base_score, cvss_version, cvss_vector, cvss_source), EPSS (epss_score, epss_percentile), CISA KEV status (cisa_kev_added_at), published_at, AI fields (gen_description, gen_cwe_id, gen_impact, gen_mitigations, gen_remediation), and trending metrics (trending_1d/7d/30d). If you only have a name or search terms, call listVulnerabilities first to find the exact identifier. For relationship pivots (e.g. related malware or attack patterns) and advanced cross-entity queries, use queryApi.
Inputs: identifier (required).
linkFindingTicketAInspect
Associate an external ticket (Jira, Linear, GitHub, ServiceNow) with one or more Mallory findings, and manage those associations. Actions: link (register a ticket against findings), attach (add more findings to a ticket already registered here), unlink (remove one finding from a ticket), list (what is linked to a finding), connections (which ticketing systems this tenant has configured).
link, attach and unlink WRITE the caller's own organization's data and take effect immediately — call them only when the user has asked for it. list and connections are read-only; call them whenever you need to know what is linked or what is configured.
TWO STEPS, BOTH REQUIRED. This tool does NOT create the ticket. Create it with the ticketing system's own tools, then call this with action "link" to register the id it returned. A ticket you created and did not register is invisible to Mallory: the finding page shows nothing, and from the user's point of view the request silently did not happen.
A CONFIGURED MALLORY TICKETING INTEGRATION IS NOT A PRECONDITION. With provider + external_id, link is a plain database write inside Mallory — it does not contact the ticketing system. Register the id even when "connections" reports nothing ready; that action answers "which systems can I use?", it does not gate linking, and skipping the link because nothing looked ready is the one failure this tool exists to prevent.
NEVER INVENT external_id, url or title. Core stores all three without checking them, and nothing corrects them later on this path, so a guessed id produces a finding that links to a ticket which does not exist. Send exactly what the provider returned when the ticket was created; omit title or url if you were not given them. url must name the same ticket as external_id — if you are not sure they agree, send external_id alone.
A SUCCESSFUL LINK MEANS MALLORY RECORDED THE ID, nothing more. It does not mean the ticket was found, read or verified. Report what you linked; do not tell the user it was checked.
One ticket often covers several findings: pass every relevant finding_uuid in a single link call rather than linking one at a time. Finding uuids come from listFindings, getFinding, or a createFinding outcome. ticket_uuid (needed by attach and unlink) is Mallory's OWN uuid for a ticket already registered here — it comes from a link outcome or the list action, and is NOT the external id like "MAL-123". Re-linking the same ticket is safe: core upserts.
Unlinking removes only the association in Mallory; the ticket stays in its own system. PLAN_LIMIT means findings are not included in this tenant's plan — the request was fine, nothing is broken and nothing was written: say so and do not retry.
Inputs: action (required), url, title, provider, +4 more.
listAdvisoriesAInspect
List and filter Mallory advisories, returning lean summaries as {items,total,offset,limit}. Each item includes: advisory title/identifier, source/vendor, severity, affected products and vulnerabilities, and published date. Filter prefixes: name:, uuid:. Sort by created_at, updated_at, published_at. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getAdvisory for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listAssetsAInspect
List and filter your organization's own asset inventory (hosts, code repositories, containers, cloud resources and more), returning core's page unchanged as {items,total,limit,next_cursor,offset,refreshed_at}. Example: which hosts have open critical vulnerabilities? Call with where='class == "host" && open_critical > 0' and sort="open_critical". To read every match, pass each page's next_cursor as cursor with the same where and sort until next_cursor is null. limit defaults to 10. If a page is refused as too large, no rows were returned: retry with half the limit and the same cursor. Pass an item's asset_uuid to getAsset for the full detail.
Inputs: sort, limit, where, cursor.
listAttackPatternsAInspect
List and filter Mallory attack patterns, returning lean summaries as {items,total,offset,limit}. Each item includes: mitre_id, name, description, tactic(s), and associated threat actors and malware. Filter prefixes: name:, uuid:, mitre_id:, tactic:. Sort by name, created_at, updated_at. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getAttackPattern for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listBreachesAInspect
List and filter Mallory breaches, returning lean summaries as {items,total,offset,limit}. Each item includes: name, description, affected organizations, record_type and loss_type, affected record counts, associated threat actors/malware/attack-patterns, and dates. Filter prefixes: name:, uuid:, loss_type:, record_type:. Sort by created_at, updated_at. For breaches linked to organizations currently matched to tenant assets, set fieldFilters matched_asset_count__gt to "0". Match age is irrelevant; use created_at for newly recorded breaches. Association does not establish victim status: verify that a matched organization is the victim. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getBreach for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listExploitsAInspect
List and filter Mallory exploits, returning lean summaries as {items,total,offset,limit}. Each item includes: title/name, description, source and maturity, and the vulnerabilities (CVEs) it targets. Filter prefixes: name:, uuid:. Sort by created_at, updated_at. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getExploit for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listFindingsAInspect
List and filter Mallory findings, returning lean summaries as {items,total,offset,limit}. Each item includes: title, status, severity, confidence, the owning definition's slug/title/category, asset type and identifier, resolution_reason, the thread_uuid of the investigation that produced it, and timestamps; the detail object adds body / summary / remediation / evidence, any linked external tickets, and entities — the threat actors, vulnerabilities and stories this finding resolved to, which is the pivot back into Mallory's intel graph. Returns every status by default — pass status=open (or status__in=open,fixed) to narrow. Sort by created_at, updated_at, status, title, severity, or asset_identifier; severity sorts INFO < LOW < MEDIUM < HIGH < CRITICAL, so desc puts Critical first. Notable fieldFilters: status, severity, definition_slug, definition_category, asset_type, asset_identifier, title, resolution_reason (also resolution_reason__isnull=true for closed findings with no reason recorded), thread_uuid to scope to one investigation. Enum values are case-sensitive and each field has its own set: severity is UPPERCASE (CRITICAL, HIGH, MEDIUM, LOW, INFO); status is lowercase and has exactly three values (open, fixed, dismissed); resolution_reason is lowercase and separate from status (false_positive, accepted_risk, not_applicable, duplicate, fixed_externally, other); definition_category is lowercase-hyphenated (e.g. public-exposure). Send values, not enum member names. definition_category is the exception: equality and membership ONLY (bare, __in, __not_in) — the __contains/__ilike/__neq the other fields accept are dropped on it, and you get the unfiltered list back. asset_type is a free-text column in provider.service.object form (e.g. aws.s3.bucket, not s3), so a partial value matches nothing unless you use asset_type__ilike. Field operators append to a field name with __: a bare field name is exact match, and the string/enum fields (status, severity, title, definition_slug, asset_type, asset_identifier, resolution_reason) also take __neq, __in, __not_in, __contains, __not_contains, __ilike. This endpoint has NO __like. Timestamps are created_at / updated_at with __gte and __lt ONLY, a half-open range — __gt, __lte and a bare created_at are not parameters at all. An operator this endpoint does not define is dropped silently rather than rejected, so guessing one returns a WIDER result set that looks filtered. Pass an item's identifier to getFinding for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listMalwareAInspect
List and filter Mallory malware, returning lean summaries as {items,total,offset,limit}. Each item includes: name/display_name plus aliases, description, capabilities, family, associated threat actors and ATT&CK techniques, related vulnerabilities, and trending activity. Filter prefixes: name:, uuid:, desc:. Sort by name, created_at, updated_at, enriched_at, or trending / trending_<m|h|d>. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getMalware for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listObservablesAInspect
List and filter Mallory observables, returning lean summaries as {items,total,offset,limit}. Each item includes: observable type (e.g. ip.v4, domain, url, hash.sha256), name/value, and verdict/opinion counts. Filter prefixes: type: (e.g. type:ip or type:ip.v4), name:, uuid:. Sort by uuid, created_at, updated_at, type, name, severity_score, confidence_score. Optional fieldFilters: scope=global|tenant, created_at__gte/__lt, severity_score__gte/__lte, confidence_score__gte/__lte, score_scope=tenant|restricted|global (tenant: only observables with the tenant's custom score; restricted: only those with the CrowdStrike combined score, for a tenant with CrowdStrike access). Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getObservable for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listOrganizationsAInspect
List and filter Mallory organizations, returning lean summaries as {items,total,offset,limit}. Each item includes: name, description, associated products and breaches, and mention activity. Filter prefixes: name:, uuid:. Sort by name, created_at, updated_at. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getOrganization for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listProductsAInspect
List and filter Mallory products, returning lean summaries as {items,total,offset,limit}. Each item includes: vendor and product name, CPE, description, and links to advisories and vulnerabilities. Filter prefixes: name:, uuid:. Sort by name, created_at, updated_at. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getProduct for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listSoftwareExtensionsAInspect
List and filter Mallory software extensions, returning lean summaries as {items,total,offset,limit}. Each item includes: extension name, marketplace/ecosystem, publisher, install count, description, and known configurations. Filter prefixes: name:, uuid:. Sort by created_at, updated_at, install_count. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getSoftwareExtension for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listSoftwarePackagesAInspect
List and filter Mallory software packages, returning lean summaries as {items,total,offset,limit}. Each item includes: package name, ecosystem, description, known configurations, supply-chain compromise evidence, and upstream OpenSSF Scorecard assessment (0–10, higher is better). Filter prefixes: name:, uuid:. Sort by created_at, updated_at, last_compromised_at, compromise_evidence_count, or openssf_score (unknown last). Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getSoftwarePackage for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listThreatActorsAInspect
List and filter Mallory threat actors, returning lean summaries as {items,total,offset,limit}. Each item includes: canonical name/display_name plus aliases, description, motivation, sponsor, family, targeted industries and source/target geographies, and trending activity. Filter prefixes: name:, uuid:, internal_name:, desc:. Sort by name, created_at, updated_at, enriched_at, or trending / trending_<m|h|d> (e.g. trending_7d). Notable fieldFilters: motivation, sponsor, family_name. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getThreatActor for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
listVulnerabilitiesAInspect
List and filter Mallory vulnerabilities, returning lean summaries as {items,total,offset,limit}. Each item includes: cve_id, description, CVSS (cvss_base_score, cvss_version, cvss_vector, cvss_source), EPSS (epss_score, epss_percentile), CISA KEV status (cisa_kev_added_at), published_at, AI fields (gen_description, gen_cwe_id, gen_impact, gen_mitigations, gen_remediation), and trending metrics (trending_1d/7d/30d). Filter prefixes: cve:, uuid:, desc:, gen_description:, gen_name:. Sort by cvss_base_score, epss_score, epss_percentile, published_at, created_at, updated_at, trending_1d/7d/30d. Range-filter via fieldFilters, e.g. {"cvss_base_score__gte":"9"} or {"published_at__gte":"2024-01-01"}. Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getVulnerability for the full detail object.
Inputs: sort, limit, order, filter, +2 more.
queryApiAInspect
Query the Mallory cybersecurity-intelligence API. Two input fields:
"path": an endpoint under /v1/ (e.g. "/v1/vulnerabilities", "/v1/actors/APT29/attack_patterns"). You can ALSO paste a Mallory web URL or path here (e.g. "https://app.mallory.ai/vulnerabilities/CVE-2025-43300", "/actors/{uuid}", "/attack-patterns/T1566", "/references/{uuid}") — it's auto-translated to the matching API endpoint, so you never need to know the URL→API mapping.
"queryParams": object of string key->value pairs for filtering, sorting, pagination
PREFER the named per-entity tools when they fit: get to fetch one by id (e.g. getVulnerability, getThreatActor, getMalware, getObservable) and list to filter many (e.g. listVulnerabilities, listThreatActors). Use THIS tool as the fallback for what they don't express: relationship pivots (e.g. /v1/actors/APT29/malware), cross-entity search (/v1/search), structured field filters and numeric/date ranges, or any endpoint they don't cover. You can also paste a Mallory web URL as the path.
DATA DOMAINS (first path segment): vulnerabilities, actors (threat actors), malware, exploits, exploitations, breaches, attack_patterns (MITRE ATT&CK), products, organizations, observables, references, stories, advisories, detections, weaknesses (CWE), industries, packages, opinions, mentions, search.
Matched-organization breaches (/v1/breaches): Set queryParams.matched_asset_count__gt="0" to select breaches linked to visible organizations with current positive asset matches for the requesting tenant. Match age is irrelevant; use created_at__gte for newly recorded breaches. Supported breach matched_asset_count operators are exact, __gt, __gte, __lt, and __lte only. All count filters must hold for a single linked organization's match row. An exact zero requires an explicit zero-count row. Association does not establish victim status: verify that a matched organization is the victim before creating a finding. Do not replace this with monitoring newly created asset-match rows.
Distribution packages (/v1/distro-packages): Use this catalog for native operating-system packages; /v1/packages is the software-package catalog. Vulnerability evidence defaults to scope=all, which includes global and current-tenant assertions. Use scope=tenant for tenant-only assertions and scope=global for global-only assertions. Filter by exact distribution, release, kind, and case-sensitive name. Read /v1/distro-packages/{uuid} for package details and /v1/distro-packages/{uuid}/builds for its builds, optionally filtering by exact, case-sensitive architecture. Read /v1/distro-package-builds/{uuid} for one build. Read /v1/distro-packages/{uuid}/vulnerabilities for current publisher vulnerability assertions, or /v1/distro-package-builds/{uuid}/vulnerabilities for package assertions and exact evidence for that build. Preserve the requested scope and paginate with limit and offset. These reads retain vendor status, native scope, fix versions, and provenance. They do not establish tenant asset exposure; missing evidence and a fixed version without an affected range do not prove an older build is safe. Core enforces the distro_packages feature gate; a 404 does not establish that a package is absent.
COMMON PATTERNS: List + filter: path="/v1/vulnerabilities" queryParams={"filter":"cve:CVE-2024","sort":"cvss_base_score","order":"desc","limit":"10"} Relationships: path="/v1/actors/APT29/malware" | path="/v1/vulnerabilities/CVE-2024-1234/threat_actors" Cross-entity: path="/v1/search" queryParams={"q":"ransomware","types":"threat_actor,malware","limit":"10"} Compromised pkgs: path="/v1/packages" queryParams={"sort":"last_compromised_at","order":"desc","limit":"20"} — recently compromised packages, newest first (use sort=compromise_evidence_count for most-compromised by count). Drill in via path="/v1/packages/{uuid}/compromises" (sorts by reported_at desc; optional compromise_type: malicious_version, account_takeover, typosquat, dependency_confusion, backdoor, supply_chain, other).
FILTER PREFIXES (inside the "filter" param; which apply depends on the endpoint): cve:, uuid:, name:, desc:, gen_name:, gen_description:, mitre_id:, tactic:, loss_type:, record_type:. No prefix = default text/name search.
FIELD OPERATORS (append to a field name with "__"): strings: __neq, __in, __not_in, __like, __ilike (case-insensitive) numbers: __neq, __gt, __gte, __lt, __lte e.g. {"cvss_base_score__gte":"9"} timestamps: __gte, __lt with ISO-8601 values e.g. {"published_at__gte":"2024-01-01"}
CVSS Vector filtering (/v1/vulnerabilities)
CVSS vector filters: cvss=AV:A/PR:N matches all slash-separated tokens within one stored assessment; cvss__in=AV:A,AV:N matches any comma-separated fragment. Both search across CVSS 2.0, 3.0, 3.1, and 4.0 assessments; prefix a fragment with CVSS:3.1/ to restrict its version. Metric names and values are case-sensitive (v2 Au differs from v4 AU), and only explicitly stored metrics match. These filters do not change the selected numeric cvss_base_score. CVSS CEL: where='cvss == "AV:A/PR:N" && epss_score >= 0.5' supports ==, !=, in, AND/OR/NOT. Keep tokens in one fragment for same-assessment AND; separate CVSS comparisons may match different assessments. Invalid fragments return HTTP 400: correct the requested filter, never retry without it.
HUNTING: Actor/malware indicator_context summarizes global plus current-tenant intelligence for the resolved observable, not an actor-specific edge; tags/roles honor requested scope. Missing context and dates/roles remain unknown. source_count does not count independent investigations. Correct a rejected filter without dropping the user's selection. Array-typed queryParams accept CSV except /v1/observables tag, whose commas are literal; repeat inline tag parameters for multiple exact values. Repeated inline array parameters retain all values.
PAGINATION/SORT: "limit" (follow the endpoint's documented bound), "offset", "sort":"", "order":"asc"|"desc".
RESPONSE: results come back as {"data": , "meta": {"endpoint","path"}}. For list / search / relationship endpoints "data" is the list envelope {"data":[...items], "total", "offset", "limit"} (items live at data.data); for a single-entity path "data" is the entity object. List responses are returned whole, exactly as the API paged them — control size with limit/offset. Semantic entity queries return an exact integer total, but descending similarity pages without a cutoff are approximate; a 503 means semantic search is temporarily unavailable (a provider failure or a very broad query timing out), never that nothing matched. Invalid, blocked, or unknown paths return a tool error (isError), not a result.
Repository data availability: An empty resolved inventory, current=null, or an unavailable inventory tool does not mean the tenant has no repositories or vulnerabilities. Check connected integrations and whether they cover the requested data. If resolved inventory lacks that coverage and an authorized integration-data transport is available, continue with connected-source data: in the in-app sandbox, load the steampipe-querying skill, discover tables for the connected provider, and use its structured query workflow (cache first; live when uncached or current state is required). Preserve existing filters and repository scope, and report source freshness and coverage differences. If this client has no such transport or no relevant integration is connected, state the coverage limitation; never substitute global threat intel for tenant evidence. Do not bypass permission denials. Offer Mallory asset-page links only when that UI is enabled for the caller; otherwise use a source-provided repository URL when available.
Note: schedule management (/v1/schedules) is not exposed over MCP in V1. Every other endpoint is scoped by your API key to your own tenant.
Resolved assets, packages, and vulnerabilities: Start with GET /v1/assets. The inventory accepts where (CEL), sort, limit, and cursor. Select hosts with where='class == "host"' and repositories with where='class == "code_repository"'. Other classes include image, datastore, deployment, domain, organization, and network_service. A network_service is one host:port/transport context an external scanner reached at one dialed address (details.via); filter it on details.address, details.port, details.protocol, details.via, details.hosting_operator, details.scope_class, details.application_group_id (one id per service name, across the addresses it resolves to) or details.response_group_id (services whose root response matched, across names). Class-specific fields are under details: for example where='class == "code_repository" && details.is_archived == false && details.primary_language == "TypeScript"'. When the evidence establishes the subject class, include it in name searches and confirm the returned asset matches before linking a finding; a unique name match from another class is not sufficient. Use display_name.contains("acme") for name search, source == "github" for a connector slug, tags["environment"] == "production" for source tags, and mallory_tags == "critical" for operator tags. Do not send old hostname, q, language, visibility or tag parameters to the unified inventory. Get the supported details fields from its where metadata; correct rejected filters without dropping the user's selection.
Resolve an identity with GET /v1/assets/by-identifier queryParams={"type":"repo_url","value":"https://github.com/owner/repo","class":"code_repository"}. The optional class also scopes host identifiers such as serial_number or fqdn. This unpaginated lookup returns items with canonical asset_uuid values. Count distinct asset_uuid values; multiple identifier rows can name one merged asset. Never choose arbitrarily among multiple assets. GET /v1/assets/{asset_uuid} follows merged UUIDs and returns requested_uuid, merged_from, current and source_records. current=null means no current source record. Use canonical links /environment/{asset_uuid}. Repository details.is_public describes repository visibility; it is not a host exposure verdict.
Read installed products at /v1/assets/{asset_uuid}/products, package dependencies at /packages, and reported vulnerabilities (including ingested Dependabot alerts) at /vulnerabilities. These are tenant observations, distinct from the global /v1/packages compromise catalog and Mallory /v1/findings. Vulnerability filters include status=open|resolved|unknown and severity (both repeatable), cvss_min (0–10), epss_min (probability 0–1), and kev=true|false. Missing or zero product/package UUIDs mean unresolved identity, not absence.
Inventory, current instances and reverse lists return {items,total,limit,next_cursor}; in the tool wrapper read data.items and data.next_cursor. Follow next_cursor with unchanged filters and sort until null. If an in-app page exceeds the response size limit, retry with a smaller limit and the same cursor and filters; no rows were returned, so do not advance the cursor. /products/history, /packages/history and /vulnerabilities/history return {asset_uuid,days,items,truncated}, oldest first; respect the retention-capped days and truncated flag. History is not cursor-paginated. GET /v1/assets/link-overrides reads link decisions; this tool cannot change them.
GET /v1/assets/groups counts current assets per value of one field: group_by is a shared column or a scalar details path (details.response_group_id, details.application_group_id, details.hosting_operator, details.port), with the same where as the inventory. List a group's members with GET /v1/assets and the where extended by <group_by> == (== null for the null key). Scanner issues on an asset are at /v1/assets/{asset_uuid}/issues (status, severity, scanner, name filters) and /issues/history; status resolved is the source's own status; an instance its scanner stops reporting leaves /issues and shows in /issues/history as absent, which is not proof of a fix. GET /v1/assets/{asset_uuid}/organizations lists the organizations that make the asset's products or host it.
Reverse lookups use GET /v1/assets/vulnerabilities/{vulnerability_uuid}/assets, /v1/assets/products/{technology_product_uuid}/assets, /v1/assets/packages/{software_package_uuid}/assets, or /v1/assets/issues/{issue_uuid}/assets. Pass class=host or class=code_repository when required; omit class for all classes. Product/package lookups also accept configuration_uuid. Use resolved UUIDs, never a CVE or package name in a UUID slot.
Timelines use /v1/assets/vulnerabilities/{vulnerability_uuid}/timeline, /v1/assets/products/{technology_product_uuid}/timeline, or /v1/assets/packages/{software_package_uuid}/timeline. Pass resolution_scope=code_repository for repositories, host for hosts, or all for every scope. Use group_by=resolution_scope for class series. Environment-tag groups can overlap: use an ungrouped series for totals. Read affected_assets for the selected scope; affected_hosts counts hosts only. Combine series only when their returned days and inclusive UTC window_end agree. An empty page or timeline does not prove complete environment coverage. A 403/404/503 is an access, identity or availability failure, not an empty inventory.
Prefer listAssets for the asset inventory list and getAsset for one asset's detail; use this tool for asset sub-resources.
Inputs: path (required), queryParams.
referenceObservablesAInspect
Get the indicators of compromise (IOCs / observables — IPs, domains, URLs, file hashes, email addresses, etc.) that Mallory extracted and attributed from a specific reference (source document). This is the 'reference → IOCs' pivot: given a threat report, return the concrete indicators it contains, so you don't have to scrape them from the report text. Provide reference as a UUID, url_hash, or a pasted Mallory reference URL. If you only have the article's web URL, first resolve it to a reference with getReference (urlFilter mode).
Inputs: reference (required), limit, offset.
searchEmbeddingsAInspect
Search the MalloryAI knowledge base using semantic similarity. This searches across all indexed cybersecurity content including articles, reports, and documentation. Use this to find relevant information about security concepts, vulnerabilities, threat intelligence, and best practices.
Inputs: query (required), limit.
searchVulnerabilitiesAInspect
Search and filter vulnerabilities in the MalloryAI database. Supports filtering by CVE ID, UUID, description, and various sorting options including CVSS score, EPSS score, and trending scores. Use this to find specific vulnerabilities, discover trending threats, or analyze vulnerability patterns. Returns comprehensive vulnerability data including: CVE ID, description, CVSS scores (base score, version, vector, source, full CVSS data array), EPSS score and percentile, CISA KEV status, publication dates, AI-generated fields (description, display name, CWE ID, impact assessment, mitigations, remediation), and trending metrics (1d, 7d, 30d).
Inputs: sort, limit, order, filter.
updateFindingAInspect
Update ONE existing Mallory finding in place — its status, severity, confidence, title, summary, body, remediation, qualifier or asset_details. Use it when new information changes an already-filed finding: the problem was fixed, it turned out not to apply, a vulnerability proved reachable, corroborating intel changes how bad it is.
WRITES IMMEDIATELY to the caller's own organization's data, and the result is visible in the Mallory UI to everyone in that organization. There is no preview and no confirmation step — calling this tool IS the write. Only call it when the user has asked for the change.
uuid identifies the finding. Get it from listFindings or getFinding, or from a createFinding DUPLICATE outcome's
existing_finding_uuid. Never construct or guess one.ONE finding per call. To change status or severity across a SET of findings you can only describe ("dismiss all the unrotated-secret findings", "mark everything on foo/bar medium"), use bulkUpdateFindings — do NOT loop this tool over a selection.
The finding's identity — definition_slug, asset_type, asset_identifier — cannot be changed. A different problem, or the same problem on a different asset, is a new finding (createFinding).
body REPLACES the stored text rather than appending to it. To add to a finding, read the current text first with getFinding and send the combined text, or the prior detail is lost. There is no evidence field on update: new evidence goes into body as prose.
asset_uuid links the finding to a resolved asset of any class. Find a name (or part of one) with GET /v1/assets using where=display_name == "" or display_name.contains(""); this searches every class and needs no class or key type. For an identity key whose kind the user provides (serial number, ARN, repo URL, digest), use GET /v1/assets/by-identifier?type=&value=; type is the identity key type, not the asset class, and class is optional. Count distinct asset_uuid values across the complete result: while there is a next_cursor, read the next page with cursor and unchanged filters and sort. A truncated or incomplete lookup cannot produce a link; with zero or multiple matches, omit asset_uuid and never guess. null removes the link and omission keeps it. It does not change asset_type or asset_identifier. For a finding whose asset_type is "host" or "asset", the link is the identity and cannot change (INVALID); create a new finding instead. Link the returned canonical asset_uuid as /environment/{asset_uuid}.
qualifier is part of core's open-finding dedupe key, so changing it can collide with another open finding on the same asset (CONFLICT).
In user-facing status messages, use "fixed" and "mark as fixed" consistently.
ENUM VALUES ARE CASE-SENSITIVE AND EACH FIELD HAS ITS OWN SET. severity is UPPERCASE (CRITICAL, HIGH, MEDIUM, LOW, INFO). status is lowercase with exactly three values: open, fixed, dismissed — "resolved", "closed" and "assigned" are not statuses, and neither are the resolution reasons (false_positive, accepted_risk, not_applicable, duplicate, fixed_externally, other), which belong to a separate field this tool does not set. Use "fixed" when the problem was remediated and "dismissed" when it is accepted or not applicable. Setting status back to "open" is allowed but unusual — the product has no reopen button — so confirm the user really means to reopen the finding.
OUTCOMES: either ok:true with the updated finding, or ok:false with a code — NOT_FOUND (no such finding in this tenant: do not retry, re-read the uuid), ASSET_NOT_FOUND (asset_uuid is not an asset of this organization: resolve it again, never guess), CONFLICT (an open finding already occupies that identity), INVALID (a rejected field, or no fields to change), PLAN_LIMIT (findings are not included in this tenant's plan — the request was fine, nothing is broken, nothing was written: say so and do not retry).
Inputs: uuid (required), body, title, status, +7 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.MIT
- AlicenseCqualityCmaintenanceCompetitor Monitor AI - MCP server providing AI-powered tools and automation by MEOK AI Labs112 npm37 PyPIMIT
- AlicenseAqualityDmaintenanceEnables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.1611 npm1MIT

industrylens-mcpofficial
AlicenseNot gradedqualityCmaintenanceBrowse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.