{"data":{"name":"io.github.cyanheads/internet-archive-mcp-server","title":null,"description":"Search the Wayback Machine and IA library (40M+ items), fetch snapshots, item metadata, and text.","version":"0.4.0","websiteUrl":null,"repositoryUrl":"https://github.com/cyanheads/internet-archive-mcp-server","remotes":[{"url":"https://internet-archive.caseyjhand.com/mcp","type":"streamable-http"}],"packages":[{"version":"0.4.0","identifier":"@cyanheads/internet-archive-mcp-server","runtimeHint":"stdio","registryType":"npm","runtimeArguments":null,"environmentVariables":null},{"version":"0.4.0","identifier":"@cyanheads/internet-archive-mcp-server","runtimeHint":"streamable-http","registryType":"npm","runtimeArguments":null,"environmentVariables":null}],"status":"active","isLatest":true,"publishedAt":"2026-10-12T20:50:08.553Z","updatedAt":"2026-10-12T20:50:08.553Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":null,"source":"official-registry","sourceId":"io.github.cyanheads/internet-archive-mcp-server","updatedAt":"2026-10-12T20:50:08.553Z","confidence":100,"websiteUrl":null,"description":"Search the Wayback Machine and IA library (40M+ items), fetch snapshots, item metadata, and text.","verification":"official","repositoryUrl":"https://github.com/cyanheads/internet-archive-mcp-server"}],"toolIndex":{"tools":[{"serverName":"io.github.cyanheads/internet-archive-mcp-server","endpointFingerprint":"a2a055887340ea25a84c927d4c2f18f3ff8b53fdd04c49b78517b71a7cb59b3d","name":"ia_find_snapshots","title":"Find Wayback Machine Snapshots","description":"Find Wayback Machine snapshots of a URL. Mode \"closest\" returns the single nearest capture to a given timestamp, or the latest capture when timestamp is omitted, via the Availability API, falling back to a CDX closest-capture query when the Availability API finds no capture or answers with a rate limit, a server error, an unreadable response, or an error in place of a capture (one result). Mode \"history\" returns the full capture list via the CDX API — filterable by date range and HTTP status code, collapsed by default to one capture per day (collapse \"timestamp:8\"); collapse \"timestamp:14\" lists one row per distinct capture second. Use history mode to survey how a page changed over time; use closest mode when you need the snapshot nearest a specific date. History mode returns up to limit records (at most 10,000 per call) and supports resume-key pagination for URLs with very large capture histories.","inputSchema":{"type":"object","properties":{"url":{"type":"string","minLength":1,"description":"The URL to look up in the Wayback Machine. A Wayback capture URL — web.archive.org/web/<timestamp>/<url>, such as a replay_url — reads as the URL it archives: history mode lists that URL's captures, and closest mode looks up its timestamp, where a timestamp naming a different one fails as ambiguous_timestamp."},"mode":{"type":"string","enum":["closest","history"],"description":"Lookup mode: \"closest\" returns the single nearest snapshot to the given timestamp, or the latest capture when timestamp is omitted; \"history\" returns the paginated full capture list via the CDX API."},"timestamp":{"description":"Target timestamp for mode \"closest\": 1–14 digits — YYYYMMDDHHMMSS or a prefix of it, such as \"20200615\" — or an ISO 8601 date or UTC date-time such as \"2020-06-15\" or \"2020-06-15T12:34:56Z\". A shorter value names a period and resolves to the capture nearest its end: \"2015\" can resolve to one from early January 2016. Omitted or blank, it is the timestamp of a Wayback capture URL passed as url, else the latest capture.","type":"string"},"from":{"description":"Start of the date range (history mode only): 1–14 digits — YYYYMMDDHHMMSS or a prefix of it — or an ISO 8601 date or UTC date-time such as \"2020-01-01\". A prefix starts at the beginning of the period it names: \"2015\" is January 1, 2015.","type":"string"},"to":{"description":"End of the date range (history mode only), in the same forms as from, and inclusive: a prefix ends at the end of the period it names, so \"2015\" reaches December 31, 2015, and \"20231231\" the end of that day.","type":"string"},"status_filter":{"description":"Filter CDX results to a specific HTTP status code (history mode only). Must be a 3-digit numeric code. Example: \"200\" to return only successful captures.","anyOf":[{"type":"string","const":""},{"type":"string","pattern":"^\\d{3}$","description":"3-digit HTTP status code."}]},"limit":{"default":100,"description":"Maximum number of CDX records to return (history mode only, default 100). One call returns at most 10,000: a larger value (up to 150,000) is served as 10,000, and the resume_key continues from there.","type":"integer","minimum":1,"maximum":150000},"collapse":{"description":"CDX collapse parameter (history mode only). Format: \"timestamp:N\" where N is 1–14 (4=year, 6=month, 8=day, 10=hour, 14=second): consecutive captures sharing the first N timestamp digits are listed once. Omitted or blank, it is \"timestamp:8\", one capture per day. Pass \"timestamp:14\" for one row per distinct capture second.","anyOf":[{"type":"string","const":""},{"type":"string","pattern":"^timestamp:\\d{1,2}$","description":"Collapse precision string."}]},"resume_key":{"description":"Opaque pagination key from a previous history mode response. Pass this to continue from where the last page left off. Server cursors expire after one hour and bind the URL and original filters; omit filters on continuation or repeat their original values. Page size may change. Wildcard and legacy raw continuations can omit collapsed captures.","type":"string"}},"required":["url","mode"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"6f554ffe0025d3fe5dd4c9a05fb4ec84eee13df465a78263a3b135b024747ceb","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:49.339Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/internet-archive-mcp-server","endpointFingerprint":"a2a055887340ea25a84c927d4c2f18f3ff8b53fdd04c49b78517b71a7cb59b3d","name":"ia_get_item","title":"Get Internet Archive Item","description":"Retrieve metadata and the file manifest for an Internet Archive item by identifier. Returns title, creator, description (as plain text), subjects, collections, license, language, publisher, ISBN, OCLC and LCCN numbers, Open Library edition and work IDs, volume, the page-image count of a text item, whether the item is access-restricted, the total file count, and a page of files, each with its format, size, and direct download URL; a file marked private cannot be downloaded. Pages hold up to max_files files (default 50, at most 500 per call) starting at file_offset; set format to keep a single file type (e.g. \"DjVuTXT\", \"Text PDF\", \"VBR MP3\"). The primary tool to act on a search result from ia_search_items. Use ia_get_text to retrieve the readable text of a text item.","inputSchema":{"type":"object","properties":{"identifier":{"type":"string","minLength":1,"description":"Internet Archive item identifier, e.g. \"prideprejudice00aust\" (Pride and Prejudice), from ia_search_items results; or an archive.org item URL, such as https://archive.org/details/prideprejudice00aust or its download, stream, metadata, or embed form, read as the identifier it names."},"format":{"description":"Keep only files whose format equals this value, ignoring case — e.g. \"DjVuTXT\", \"Text PDF\", \"VBR MP3\". Applied before paging. Omit to list every format.","type":"string"},"max_files":{"default":50,"description":"Maximum number of files to return (default 50). One call returns at most 500: a larger value (up to 300,000) is served as 500, with a notice naming the next file_offset.","type":"integer","minimum":1,"maximum":300000},"file_offset":{"default":0,"description":"Zero-based position in the (format-filtered) file list to start from (default 0). To read the next page, add the number of files returned to the previous file_offset, or pass the file_offset the notice names.","type":"integer","minimum":0,"maximum":9007199254740991}},"required":["identifier"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"5d8b0897f8baf0a803ae8e45761bb86c9419f257bf53dfab9920e1ed406807b0","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:49.339Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/internet-archive-mcp-server","endpointFingerprint":"a2a055887340ea25a84c927d4c2f18f3ff8b53fdd04c49b78517b71a7cb59b3d","name":"ia_get_snapshot","title":"Get Wayback Machine Snapshot Content","description":"Fetch the archived content of a URL at a specific Wayback Machine timestamp, or of the capture a Wayback capture URL such as a replay_url names. Resolves to the nearest available capture when the exact timestamp has no snapshot. Returns the capture as text — an HTML page as readable plain text with its markup stripped, another text type (plain text, JSON, XML, JavaScript) as stored — and the replay URL of the capture Wayback served, for browser access. A capture of a PDF, image, or other non-text file fails as non_text_capture. Long text comes one page at a time: has_more and total_chars say what remains, and char_offset reads further — pass resolved_timestamp as timestamp so every page comes from the same capture. Use ia_find_snapshots first to discover valid timestamps for a URL.","inputSchema":{"type":"object","properties":{"url":{"type":"string","minLength":1,"description":"The URL whose archived content to retrieve. A Wayback capture URL — web.archive.org/web/<timestamp>/<url>, such as a replay_url — reads as the URL it archives at its timestamp; a timestamp naming a different one fails as ambiguous_timestamp."},"timestamp":{"type":"string","description":"Target Wayback timestamp: 1–14 digits — YYYYMMDDHHMMSS or a prefix of it — or an ISO 8601 date or UTC date-time such as \"2020-01-01\" or \"2020-01-01T12:00:00Z\". A full 14 digits, such as resolved_timestamp or a timestamp from ia_find_snapshots, reads that capture, or the one Wayback redirects it to; a shorter value names a period and resolves to the capture nearest its end (\"2015\" can resolve to one from early January 2016); blank reads the timestamp of a Wayback capture URL passed as url, else the latest capture. Example: \"20200101120000\" for noon on January 1, 2020."},"char_offset":{"default":0,"description":"Character offset (UTF-16 code units) into the capture's text where this page starts. For the next page, pass the previous char_offset plus max_chars, with the previous resolved_timestamp as timestamp so the page comes from the same capture. An offset at or past total_chars returns empty text.","type":"integer","minimum":0,"maximum":9007199254740991},"max_chars":{"description":"Maximum characters this page holds. Defaults to the server-configured maximum (IA_MAX_SNAPSHOT_CHARS, typically 50 000); a larger value is served at that maximum, with a notice.","type":"integer","minimum":1,"maximum":9007199254740991}},"required":["url","timestamp"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"b9156192720532555c35ba006aca51b1170d0b34dd262bc21f5c2a5274b022dc","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:49.339Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/internet-archive-mcp-server","endpointFingerprint":"a2a055887340ea25a84c927d4c2f18f3ff8b53fdd04c49b78517b71a7cb59b3d","name":"ia_get_text","title":"Get Internet Archive Item Text","description":"Retrieve readable OCR DjVuTXT or plain text from an Internet Archive item, including public-domain books, documents, scanned periodicals, and transcripts. Each call reads one text file: the one file names, or by default the first DjVuTXT file (else Text, Plain Text, or another .txt file). An item can hold several, such as one per volume; a notice then gives the count. Set max_chars for page size, then pass next_continuation as continuation with the same identifier and omit char_offset. Direct char_offset access remains available. To list the DjVuTXT files of an item, call ia_get_item with format \"DjVuTXT\".","inputSchema":{"type":"object","properties":{"identifier":{"type":"string","minLength":1,"description":"Internet Archive item identifier, e.g. \"prideprejudice00aust\" (Pride and Prejudice), from ia_search_items results; or an archive.org item URL, such as https://archive.org/details/prideprejudice00aust or its download, stream, metadata, or embed form, read as the identifier it names. A download, stream, or storage-node URL naming a file reads that file when file is omitted."},"max_chars":{"description":"Maximum number of characters to return in this response. Defaults to the server-configured maximum (IA_MAX_SNAPSHOT_CHARS, typically 50 000); a larger value is served at that maximum, with a notice. Lower values reduce token usage.","type":"integer","minimum":1,"maximum":9007199254740991},"char_offset":{"description":"Character offset to start reading from (default 0). For sequential pages use next_continuation as continuation instead. Omit char_offset when using continuation.","type":"integer","minimum":0,"maximum":9007199254740991},"continuation":{"description":"Opaque next_continuation from the previous page. Omit char_offset when using it; blank is omitted.","type":"string"},"file":{"description":"The text file to read, named exactly as ia_get_item lists it, e.g. \"Strabo 02 Geography 3-5_djvu.txt\". It must be readable text: format DjVuTXT, Text, or Plain Text, or a .txt name whose format is not Metadata. Omit to read the default: the first DjVuTXT file, else Text, else Plain Text, else another .txt file. With continuation, omit it or name the file the continuation reads; blank is omitted.","type":"string"}},"required":["identifier"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"69e48108da484b182d98662bbd9dd02c19678fcf054a1b8551f440cafb35c06a","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:49.339Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/internet-archive-mcp-server","endpointFingerprint":"a2a055887340ea25a84c927d4c2f18f3ff8b53fdd04c49b78517b71a7cb59b3d","name":"ia_search_items","title":"Search Internet Archive Items","description":"Search the Internet Archive library (40M+ items) using the Advanced Search (Solr) API. Filter by media type (texts, audio, movies, software, image, etc.), collection, creator, date range, and language. Sort by downloads (the default), date, title, or random. Supports pagination via page/rows. Returns identifiers, titles, creators (the first 10, with creator_count when a record lists more), media types, dates, download counts, collections (without fav- favorites lists), total_found, and current page/rows for pagination context. Use ia_get_item with a returned identifier to get full metadata and file manifests.","inputSchema":{"type":"object","properties":{"query":{"type":"string","minLength":1,"maxLength":2047,"description":"Solr query string. Supports field prefixes such as title:\"war and peace\", creator:dickens, subject:history. Plain keywords search all fields. Put a URL in quotes. At most 2,047 characters, a limit the filters below also count toward."},"mediatype":{"description":"Filter by media type: texts, movies, audio, software, image, data, web, collection, etree (live concert recordings), or account. Case-insensitive; text, book, and books mean texts, movie, video, and videos mean movies, images means image, and collections means collection. Any other value is rejected.","type":"string"},"collection":{"description":"Filter to items within a collection, given by identifier, e.g. \"gutenberg\" or \"librivoxaudio\", or by its archive.org details URL, e.g. https://archive.org/details/gutenberg.","type":"string"},"creator":{"description":"Filter by creator name, e.g. \"Charles Dickens\". Matches a creator holding every word of the name close together, in any order and case-insensitively, so \"Charles Dickens\" also finds \"Dickens, Charles, 1812-1870\" and \"Charles John Huffam Dickens\". For an exact phrase, put creator:\"Charles Dickens\" in query instead. Must contain a letter or digit.","type":"string"},"date_from":{"description":"Inclusive start of date range: YYYY, YYYY-MM, or YYYY-MM-DD. A year or month starts on its first day; blank means no lower bound. Must be a real Gregorian date.","type":"string"},"date_to":{"description":"Inclusive end of date range: YYYY, YYYY-MM, or YYYY-MM-DD. A year or month ends on its last day; blank means no upper bound. Must be a real Gregorian date.","type":"string"},"language":{"description":"Filter by language: an ISO 639-1, ISO 639-2, or discontinued MARC code, or an English name, e.g. \"eng\", \"en\", \"English\", or \"fre\". Case-insensitive. A known language matches records under any of its codes and names (\"fr\" also finds \"fre\", \"fra\", and \"French\"), except a two-letter code that is also an English word (am, an, as, be, he, hi, is, it, my, no, or, so, to), matched only when it is the value given; any other value is matched as given. For a single spelling, put language:\"eng\" in query instead. Must contain a letter or digit.","type":"string"},"sort":{"description":"Sort order in Solr format: a sortable field followed by asc or desc, e.g. \"downloads desc\", \"date asc\", \"publicdate desc\", \"titleSorter asc\", or \"random\". Default: \"downloads desc\". Advanced Search has no relevance sort. Except under random, results tied under the sort are ordered by identifier, so consecutive pages neither repeat nor skip an item.","type":"string"},"rows":{"default":50,"description":"Number of results per page (default 50). One call returns at most 200: on page 1 a larger value (up to 10,000) is served as 200 with a notice naming the next page; on later pages a value above 200 is rejected.","type":"integer","minimum":1,"maximum":10000},"page":{"default":1,"description":"Page number (1-indexed). Combine with rows for pagination. Advanced Search serves only the first 10,000 results, so page × rows ≤ 10,000 (page 50 at 200 rows, page 200 at 50).","type":"integer","minimum":1,"maximum":9007199254740991}},"required":["query"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"openWorldHint":true},"definitionHash":"e6d88cfee6c8ebfe0560b5ee00ae5fc186cb03c737f96c1d6e9b00aafaf80d6d","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:49.339Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"a2a055887340ea25a84c927d4c2f18f3ff8b53fdd04c49b78517b71a7cb59b3d","protocol":"streamable-http","status":"indexed","toolCount":5,"observedAt":"2026-11-19T07:46:49.339Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"io.github.cyanheads/internet-archive-mcp-server":{"url":"https://internet-archive.caseyjhand.com/mcp"}}},"Cursor":{"mcpServers":{"io.github.cyanheads/internet-archive-mcp-server":{"url":"https://internet-archive.caseyjhand.com/mcp"}}},"VS Code":{"servers":{"io.github.cyanheads/internet-archive-mcp-server":{"type":"http","url":"https://internet-archive.caseyjhand.com/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://internet-archive.caseyjhand.com/mcp"},{"protocol":"mcp","package":"@cyanheads/internet-archive-mcp-server","registryType":"npm","version":"0.4.0"},{"protocol":"mcp","package":"@cyanheads/internet-archive-mcp-server","registryType":"npm","version":"0.4.0"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:io.github.cyanheads%2Finternet-archive-mcp-server","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/io.github.cyanheads%2Finternet-archive-mcp-server","name":"io.github.cyanheads/internet-archive-mcp-server","description":"Search the Wayback Machine and IA library (40M+ items), fetch snapshots, item metadata, and text.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://internet-archive.caseyjhand.com/mcp"},{"protocol":"mcp","package":"@cyanheads/internet-archive-mcp-server","registryType":"npm","version":"0.4.0"},{"protocol":"mcp","package":"@cyanheads/internet-archive-mcp-server","registryType":"npm","version":"0.4.0"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":null,"repositoryUrl":"https://github.com/cyanheads/internet-archive-mcp-server","version":"0.4.0"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"io.github.cyanheads/internet-archive-mcp-server","status":"online","lastCheckedAt":"2026-11-20T09:18:05.968Z","lastSuccessfulCheck":"2026-11-20T09:18:05.968Z","latencyMs":255,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T09:18:05.968Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T09:18:05.968Z"},"security":null,"timestamps":{"createdAt":"2026-10-12T20:50:08.553Z","updatedAt":"2026-10-12T20:50:08.553Z","observedAt":"2026-11-20T09:18:05.968Z"},"compatibility":{"serverVersion":"0.4.0","protocolVersions":[{"protocol":"mcp","version":null}]}}}}