{"$schema":"https://verifymcp.io/schemas/trust-report.json","schemaVersion":1,"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"generatedAt":"2026-11-22T00:04:03.772Z","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp","markdownUrl":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp.md","server":{"slug":"com-benchlet-incidentlib","name":"Incident Library","registryName":"com.benchlet/incidentlib","description":"Public post-incident reports as structured cases: search by symptom, read one, list by cause.","registryStatus":"active","deletedAt":null,"statusMessage":null,"liveness":"live","publisher":{"class":"unknown","claimed":false}},"component":{"slug":"incidentlib-mcp","type":"remote","identifier":"https://incidentlib-mcp.benchlet.com/mcp","withdrawn":false,"url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp","version":"1.0.1","transport":null,"scoredAt":"2026-11-21T07:54:45.361Z"},"score":{"total":78,"tier":"medium","status":"scored","weekDelta":4,"history":[{"date":"2026-11-21","total":78},{"date":"2026-11-20","total":78},{"date":"2026-11-19","total":77},{"date":"2026-11-18","total":77},{"date":"2026-11-17","total":76},{"date":"2026-11-16","total":76},{"date":"2026-11-15","total":74},{"date":"2026-11-14","total":74},{"date":"2026-11-13","total":73},{"date":"2026-11-12","total":73},{"date":"2026-11-11","total":72},{"date":"2026-11-10","total":65}]},"categories":[{"name":"Endpoint Security","score":83,"verdict":"partial","reasons":["The endpoint's TLS certificate is valid, in date, and uses a strong key.","No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.","HTTPS is enforced; there's no plaintext access path.","The HSTS (Strict-Transport-Security) header is present.","DNSSEC is configured correctly; the domain's records validate against the full chain to the root."],"codes":[{"code":"tls.valid","args":{}},{"code":"auth.none_no_destructive","args":{}},{"code":"https.enforced","args":{}},{"code":"headers.hsts_present","args":{}},{"code":"dnssec.validated","args":{}}]},{"name":"Transport & Reachability","score":100,"verdict":"pass","reasons":["Verified streamable-http transport via a live MCP handshake."],"codes":[{"code":"transport.verified","args":{"transport":"streamable-http"}}]},{"name":"Schema Quality & AI Usability","score":65,"verdict":"fail","reasons":["AI-judged instruction clarity (excellent).","Context-footprint check failed: tool/resource definitions use about 1539 tokens (~307/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.","Usage-examples check failed: none of the tools include examples."],"codes":[{"code":"schema.ai_quality","args":{"band":"excellent"}},{"code":"schema.footprint_heavy","args":{"avg":"307","items":"5","tools":"5","tokens":"1539","resources":"0"}},{"code":"schema.examples_absent","args":{}}]},{"name":"Stability & Change Management","score":37,"verdict":"partial","reasons":["Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses."],"codes":[{"code":"stability.building_history","args":{"days":"11"}}]},{"name":"Tool Coverage","score":100,"verdict":"pass","reasons":["100% of tools have a non-trivial description (not blank, and not just the tool's name).","100% of tool parameters carry a description."],"codes":[{"code":"toolquality.descriptions","args":{"pct":"100"}},{"code":"toolquality.param_docs","args":{"pct":"100"}}]},{"name":"Tool Safety","score":100,"verdict":"pass","reasons":["No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.","We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.","An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it."],"codes":[{"code":"toolsafety.injection_clean","args":{}},{"code":"toolsafety.destructive_none","args":{"tools":"5"}},{"code":"toolsafety.manipulation_clean","args":{"units":"5","judged":"5"}}]},{"name":"Capabilities","score":100,"verdict":"pass","reasons":["Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28."],"codes":[{"code":"protocol.supported","args":{"latest":"2026-07-28","version":"2025-11-25"}}]}],"inconclusive":[],"malware":[],"components":[{"slug":"incidentlib-mcp","type":"remote","identifier":"https://incidentlib-mcp.benchlet.com/mcp","withdrawn":false,"score":78,"current":true,"url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp","markdownUrl":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp.md"}],"facts":[{"label":"Endpoint","value":"https://incidentlib-mcp.benchlet.com/mcp"},{"label":"Transports","value":"streamable-http"},{"label":"Auth","value":"none"},{"label":"Version","value":"1.0.1"}],"install":{"available":true,"bundleSha256":null},"tools":[{"name":"search_incidents","title":"Search incidents by symptoms","description":"Use first, whenever someone describes a failure they are seeing. Pass the symptoms as a sentence or a few words, in English or Korean; returns the reviewed public post-incident reports that answer it, best match first: the search ranks every case and keeps only those judged relevant to the sentence, usually a handful, and none when the library has no such incident (`total` 0). `total` is how many, `results` is one page of them in full (each with the case id, the page url and the source link), `matched` is every one as a row, and `next_cursor` fetches the next page. `interpreted` lists the values the sentence named (the search moves cases carrying them up) and any organisation it named (a filter to choose, not a ranking signal); `facets` count the results by root cause, component, symptom, contributing factor and organisation with the case ids, which answers 'what usually caused this' from the same call. The optional slug filters keep only cases carrying those values (AND); take slugs from facets, interpreted or vocab. Follow with get_incident for the full case.","inputs":[{"name":"component","type":"string","required":false,"description":"Keep only cases with this component slug, e.g. coredns"},{"name":"cursor","type":"string","required":false,"description":"next_cursor from the previous page"},{"name":"domain","type":"string","required":false,"description":"Keep only cases in this domain, e.g. kubernetes or ai-infra"},{"name":"factor","type":"string","required":false,"description":"Keep only cases with this contributing factor slug, e.g. no-alerting"},{"name":"lang","type":"string","required":false,"description":"ko returns the Korean text of each field where the reviewers wrote one"},{"name":"limit","type":"integer","required":false,"description":"Cases per page"},{"name":"org","type":"string","required":false,"description":"Keep only cases of this organisation, by slug, e.g. github (from facets.orgs, interpreted or vocab)"},{"name":"root_cause","type":"string","required":false,"description":"Keep only cases with this root cause slug, e.g. capacity"},{"name":"symptom","type":"string","required":false,"description":"Keep only cases with this symptom slug, e.g. pod-pending"},{"name":"symptoms","type":"string","required":false,"description":"What is observed, as a sentence or a few words, e.g. 'pods cannot get an IP, nodes show no available addresses' or 'coredns oom'. Leave it out to list every case under the slug filters, newest first;…"}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":492},{"name":"get_incident","title":"Get one incident","description":"Returns one case in full by its id: the structured write-up (symptoms, trigger, root cause, components, contributing factors, summary, impact, timeline, detection, remediation, action items, lessons), its sources with archived copies, and `similar_cases`. Use after search_incidents, list_incidents or get_topic has given you a case id; not for finding cases (use search_incidents for symptoms, list_incidents or get_topic for a category). `lang: ko` returns the Korean text of each field where the reviewers wrote one, otherwise English. The id must look like IL-0007; an id of that shape that matches no approved case returns an error result saying so, and an id of another shape is rejected before the call. Every call for the same id returns the same case.","inputs":[{"name":"id","type":"string","required":true,"description":"Case id such as IL-0007"},{"name":"lang","type":"string","required":false,"description":"ko returns the Korean text of each field where the reviewers wrote one"}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":209},{"name":"list_incidents","title":"List incidents by vocabulary value","description":"Lists cases by category, newest first, one page at a time: `count` and `cases` (id, title, organisation, date, root cause, page url), plus `next_cursor` when more remain; call again with `cursor` for the following page. Use when the question names a category (a root cause, component, symptom, contributing factor, domain or organisation) rather than a symptom sentence; for a sentence use search_incidents, and for one category with its related categories counted use get_topic. Each filter is a slug (kebab-case) of its own kind: `symptom` is what was observed (pod-pending), `factor` is a condition that made it worse (no-alerting), `root_cause` is why it happened (capacity). Filters combine with AND. An unknown slug returns count 0 with no error; find the slug with vocab when you only have words. Reads only; the same filters return the same page.","inputs":[{"name":"component","type":"string","required":false,"description":"e.g. coredns, vpc-cni"},{"name":"cursor","type":"string","required":false,"description":"next_cursor from the previous page"},{"name":"domain","type":"string","required":false,"description":"kubernetes or ai-infra"},{"name":"factor","type":"string","required":false,"description":"contributing factor, e.g. no-alerting"},{"name":"lang","type":"string","required":false,"description":"ko returns the Korean text of each field where the reviewers wrote one"},{"name":"limit","type":"integer","required":false,"description":"Cases per page"},{"name":"org","type":"string","required":false,"description":"the organisation's slug, e.g. github"},{"name":"root_cause","type":"string","required":false,"description":"e.g. capacity, config-change"},{"name":"symptom","type":"string","required":false,"description":"e.g. pod-pending"}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":344},{"name":"get_topic","title":"Get a root cause, component, symptom, contributing factor or organisation","description":"Returns one vocabulary value with every case that carries it and, under `related`, the other four kinds counted over those cases with case ids: for a symptom, the root causes behind it (answers 'what usually causes this'); for a root cause, the components and factors seen with it. Use when you already have a slug and want the picture around it; use vocab to find the slug from words, list_incidents for a plain paged list, search_incidents for a symptom sentence. `kind` is the slug's category: root_causes, components, symptoms, factors or orgs (the organisations that published cases). With `symptoms`, the page keeps only the cases that sentence finds, best match first, and `query` echoes it, so 'certificate expiry, but only where DNS was involved' is one call. The answer is not paged: `count` and `cases` hold every case of the value (at most a few dozen today). An unknown slug or a slug of the wrong kind returns an error result naming it; nothing is written.","inputs":[{"name":"kind","type":"string","required":true,"description":"Which category the slug belongs to"},{"name":"slug","type":"string","required":true,"description":"The value's slug, e.g. capacity, coredns, pod-pending, no-alerting, github"},{"name":"symptoms","type":"string","required":false,"description":"A symptom sentence that restricts the page to the cases it finds"}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":289},{"name":"vocab","title":"Vocabulary: slugs and their names","description":"Resolves words to vocabulary slugs for the filters of search_incidents, list_incidents and get_topic. With `query`, returns `matches`: the `limit` values nearest in meaning to the words, nearest first, each with kind, slug, English and Korean name and page url (e.g. 'cert ran out' finds certificate-expiry); `kind` restricts to one category. There is no similarity cutoff: the list is always `limit` long, so when the words name nothing in the library the matches are far from them; read the names before using a slug, and when none fits, search with search_incidents instead of filtering. Without `query`, returns every value of every kind with names, aliases and definitions (a large answer; prefer `query`). Reads only.","inputs":[{"name":"kind","type":"string","required":false,"description":"Only this kind"},{"name":"limit","type":"integer","required":false,"description":"Values to return"},{"name":"query","type":"string","required":false,"description":"A few words naming what you are looking for"}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":205}],"toolsTruncatedAtCapture":false,"diagnostics":{"capturedAt":"2026-11-21T07:54:45.000Z","track":"remote","endpoint":"https://incidentlib-mcp.benchlet.com/mcp","declaredUrl":null,"truncated":false,"tls":{"outcome":"valid","label":"Valid","version":"TLS 1.3","cipherSuite":"TLS_AES_256_GCM_SHA384","chainError":null,"certificates":[{"subject":"CN=incidentlib-api.benchlet.com","issuer":"CN=YR2,O=Let's Encrypt,C=US","notBefore":"2026-11-08T13:57:23Z","notAfter":"2027-02-06T13:57:22Z","keyType":"RSA","keyBits":2048,"isCa":false},{"subject":"CN=YR2,O=Let's Encrypt,C=US","issuer":"CN=Root YR,O=ISRG,C=US","notBefore":"2025-09-03T00:00:00Z","notAfter":"2028-09-02T23:59:59Z","keyType":"RSA","keyBits":2048,"isCa":true},{"subject":"CN=Root YR,O=ISRG,C=US","issuer":"CN=ISRG Root X1,O=Internet Security Research Group,C=US","notBefore":"2026-05-13T00:00:00Z","notAfter":"2032-09-02T23:59:59Z","keyType":"RSA","keyBits":4096,"isCa":true}]},"dnssec":{"result":"secure","label":"Secure","name":"incidentlib-mcp.benchlet.com.","steps":[{"zone":".","outcome":"verified","label":"Verified"},{"zone":"com.","outcome":"verified","label":"Verified"},{"zone":"benchlet.com.","outcome":"verified","label":"Verified"},{"zone":"incidentlib-mcp.benchlet.com.","outcome":"verified","label":"Verified"}]},"auth":{"outcome":"none","label":"No authorisation required","gate":null,"gateLabel":null,"status":200,"authorizationServers":[]},"httpsRedirect":{"outcome":"https_enforced","label":"HTTPS enforced","status":308},"transports":[{"transport":"streamable-http","outcome":"verified","label":"Verified","status":200,"followed":false}],"provenance":null,"installScripts":[],"installScriptsTotal":null,"vulnerabilities":[],"vulnerabilitiesTotal":null,"dependencies":null},"mismatches":[],"changelog":{"trackingSince":"2026-11-10","recent":[{"id":"chg_01a1f7fc-6e63-7979-9a8e-796ab30c8634","kind":"score.total_changed","summary":"Trust score (77 → 78)","materiality":"functional","direction":"improvement","scoreDelta":1,"occurredOn":"2026-11-20","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1f7fc-6e63-7979-9a8e-796ab30c8634"},{"id":"chg_01a1eda2-2870-75e4-a820-9caaaf1f4f20","kind":"score.total_changed","summary":"Trust score (76 → 77)","materiality":"functional","direction":"improvement","scoreDelta":1,"occurredOn":"2026-11-18","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1eda2-2870-75e4-a820-9caaaf1f4f20"},{"id":"chg_01a1e355-0c3f-7ebb-b816-d65897b978d8","kind":"check.verdict","summary":"DNSSEC (fail → pass)","materiality":"security","direction":"improvement","scoreDelta":null,"occurredOn":"2026-11-16","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1e355-0c3f-7ebb-b816-d65897b978d8"},{"id":"chg_01a1e355-0c45-7afd-af50-7763e227d7bd","kind":"score.total_changed","summary":"Trust score (74 → 76)","materiality":"functional","direction":"improvement","scoreDelta":2,"occurredOn":"2026-11-16","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1e355-0c45-7afd-af50-7763e227d7bd"},{"id":"chg_01a1de31-5ea1-704d-bc78-e6bb80ac93b0","kind":"tool.description_changed","summary":"Tool “search_incidents” rewrote its description, which is the text the model reads","materiality":"security","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-15","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1de31-5ea1-704d-bc78-e6bb80ac93b0"},{"id":"chg_01a1d908-52cf-7211-a519-5d705cac3ad2","kind":"score.total_changed","summary":"Trust score (73 → 74)","materiality":"functional","direction":"improvement","scoreDelta":1,"occurredOn":"2026-11-14","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1d908-52cf-7211-a519-5d705cac3ad2"},{"id":"chg_01a1ceba-e7de-7ef2-a6f0-31352da7d2cb","kind":"check.measure","summary":"Schema quality (213 → 298)","materiality":"functional","direction":"regression","scoreDelta":null,"occurredOn":"2026-11-12","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1ceba-e7de-7ef2-a6f0-31352da7d2cb"},{"id":"chg_01a1ceba-e7e1-78ca-829d-fd4bc1f1947c","kind":"tool.description_changed","summary":"Tool “get_incident” rewrote its description, which is the text the model reads","materiality":"security","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-12","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1ceba-e7e1-78ca-829d-fd4bc1f1947c"},{"id":"chg_01a1ceba-e7e2-7a9f-adca-460e031f58ac","kind":"tool.description_changed","summary":"Tool “get_topic” rewrote its description, which is the text the model reads","materiality":"security","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-12","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1ceba-e7e2-7a9f-adca-460e031f58ac"},{"id":"chg_01a1ceba-e7e3-730c-a0cd-b0d53642855b","kind":"tool.description_changed","summary":"Tool “list_incidents” rewrote its description, which is the text the model reads","materiality":"security","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-12","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1ceba-e7e3-730c-a0cd-b0d53642855b"},{"id":"chg_01a1ceba-e7e3-7c08-b3df-97a044b044ab","kind":"tool.description_changed","summary":"Tool “vocab” rewrote its description, which is the text the model reads","materiality":"security","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-12","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1ceba-e7e3-7c08-b3df-97a044b044ab"},{"id":"chg_01a1ceba-e7e4-7708-a1ca-240782a5fb4d","kind":"score.total_changed","summary":"Trust score (72 → 73)","materiality":"functional","direction":"improvement","scoreDelta":1,"occurredOn":"2026-11-12","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1ceba-e7e4-7708-a1ca-240782a5fb4d"},{"id":"chg_01a1c841-e655-7128-b93a-dbd101922038","kind":"check.reverified","summary":"Authorization (unverified → partial)","materiality":"security","direction":"improvement","scoreDelta":null,"occurredOn":"2026-11-11","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c841-e655-7128-b93a-dbd101922038"},{"id":"chg_01a1c841-e655-7b41-8dab-49f136464e42","kind":"check.reverified","summary":"Stability (unverified → 0.03)","materiality":"functional","direction":"improvement","scoreDelta":null,"occurredOn":"2026-11-11","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c841-e655-7b41-8dab-49f136464e42"},{"id":"chg_01a1c841-e656-70f9-82f3-351c51d1ef5a","kind":"check.measure","summary":"Tool coverage (93% → 100%)","materiality":"functional","direction":"improvement","scoreDelta":null,"occurredOn":"2026-11-11","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c841-e656-70f9-82f3-351c51d1ef5a"},{"id":"chg_01a1c841-e656-7583-b37c-8a8c169c7249","kind":"check.measure","summary":"Schema quality (good → excellent)","materiality":"functional","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-11","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c841-e656-7583-b37c-8a8c169c7249"},{"id":"chg_01a1c841-e656-7a9c-a18a-4ffee5a485dc","kind":"param.description_changed","summary":"“get_topic” reworded the description of “kind”","materiality":"cosmetic","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-11","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c841-e656-7a9c-a18a-4ffee5a485dc"},{"id":"chg_01a1c841-e656-7e9f-be80-9432a2551374","kind":"param.description_changed","summary":"“vocab” reworded the description of “limit”","materiality":"cosmetic","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-11","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c841-e656-7e9f-be80-9432a2551374"},{"id":"chg_01a1c841-e657-737c-9dfe-df02966e08fd","kind":"score.total_changed","summary":"Trust score (65 → 72)","materiality":"functional","direction":"improvement","scoreDelta":7,"occurredOn":"2026-11-11","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c841-e657-737c-9dfe-df02966e08fd"},{"id":"chg_01a1c69e-630c-7dbe-9429-4636ff7d6514","kind":"score.first_scored","summary":"First indexed and scored","materiality":"functional","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-10","url":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp#chg-chg_01a1c69e-630c-7dbe-9429-4636ff7d6514"}],"truncated":false,"feedUrl":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp/changelog.json"},"links":{"html":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp","markdown":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp.md","changelogJson":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp/changelog.json","changelogRss":"https://verifymcp.io/servers/com-benchlet-incidentlib/incidentlib-mcp.xml","external":[{"label":"Remote endpoint","href":"https://incidentlib-mcp.benchlet.com/mcp"},{"label":"Repository","href":"https://github.com/Team-DogFoot/incidentlib-reports"},{"label":"Website","href":"https://benchlet.com/incidentlib/"}]}}