omniseek
OmniSeek gives an AI agent a curated, private search-and-research layer over sources web search doesn't reach — Chinese communities, podcasts/video speech, and citation graphs — with local memory of what it finds.
Search across sources (
omniseek_search): one deduped, ranked list across the whole catalog, cross-lingual + semantic, with raw per-source buckets or a single-source deep drill; fire-then-collect for faster, more complete results.Route and orient (
omniseek_sources): list sources by domain, region, query, or health before searching.Read anything (
omniseek_read): turn any URL or document (PDF, pptx, docx, xlsx) into windowed, structured text.See images (
omniseek_view): document figures, loose image URLs, and sampled video frames delivered to your own vision.Transcribe speech (
omniseek_transcribe): local, private ASR for Bilibili, podcasts, audio files — sliced by timestamp, with optional speaker diarization.Map research fields (
omniseek_field_skeleton): citation neighborhood of a field — foundational core vs. frontier, with edges for your own clustering.Paper utilities:
omniseek_paper_recommend(SPECTER similarity),omniseek_paper_enrich(open-access PDF, retraction status, citation count).People and labs:
omniseek_resolve_identity(author disambiguation),omniseek_coauthors(collaboration network),omniseek_institution_cohort(who publishes at a lab in a field).Accumulated evidence graph (
omniseek_graph): find, neighborhood, between, voices, since, similar — bounded, provenance-typed, read-only.Record judgments:
omniseek_ruling(same/not-same identity) andomniseek_statement(directed typed relations) feed back into future graph views and search hits.Monitor topics (
omniseek_sensor): saved searches on a schedule that report only what's new, with keyword filters and absence detection.Curate sources (
omniseek_curator_view/omniseek_curator_act): propose, probe, admit, retire, and audit catalog sources.Parallelize (
omniseek_gather): run up to 10 read-only tools in one response.Investigate via the
investigateMCP prompt (person, lab, field, product, chase).Private by design: runs locally, no account, no telemetry, login-walled sites off by default and only via your own browser login.
Allows reading and normalizing arXiv papers into clean text, enabling academic research workflows.
Integrates with Xiaohongshu as a login-walled source, enabling search through the user's own authenticated browser.
Give your AI agent the parts of the internet web search doesn't reach.
OmniSeek is an add-on for AI assistants and agents like Claude Code, Cursor, and Codex that lets them search where web search stops.
Ask in English, get what people actually said on Bilibili, and Zhihu when you ask for it, with links to the original posts.
Get the papers a research field is built on, and the recent ones building on them, in one answer.
Have your agent watch a topic and tell you only what is new since last time.
uv tool install omniseek
claude mcp add omniseek -- omniseekRuns on your own computer. It plugs in through MCP, the standard way AI apps like Claude Code and Cursor add tools. Cursor and Codex: one line each, see Install.
See the difference
One real question, asked in Chinese: in Mu Li's 87-minute Bilibili walkthrough of the Transformer paper, what does he say about the paper's writing, and at what minute?
Web search answered from other people's notes: "around minutes 1 to 8", and asked again, "between about 1:50 and 2:30". A search for his exact words found nothing.
With OmniSeek, the agent transcribed all 87 minutes locally and found the line at 1:21:51: 「这篇文章的写作是非常简洁的,因为就是说他每一句话就基本上在讲一件事情。」 "The writing of this paper is very concise: basically, every sentence says one thing." Asked again, it gave the same line from cache in 0.1 s.
The full comparison on three questions, with sources, dates, and a short video.
Related MCP server: Augent
What your agent can reach
Chinese communities: Bilibili videos and comments, Zhihu answers when you ask for them, recent V2EX threads, all with links to the posts. More: Bilibili, Zhihu
Across languages: ask in English, search in Chinese, answer in English. And the reverse. More
Podcasts and videos: turns speech into text on your own computer and quotes it with the minute (optional add-on). More
Research papers: which papers a field is built on and which recent ones cite them. More
New since last time: save a search once; each rerun shows only what is new. More
Sites you log in to: if you switch it on, your agent reads them through your own browser login. Off by default. More
It also keeps what it finds in a local index on your computer, so later searches start from what it already knows.
Install
The two commands above are all you need, with Python 3.11 or newer (uv installs it if you don't have it). Your AI app starts OmniSeek when it needs it. Nothing to keep running, no port to open.
Cursor, Codex, pipx, Docker, and the optional add-ons (podcast transcription, PDF reading, sites you log in to) are in Install.
Your data, your logins
OmniSeek runs on your computer. There is no OmniSeek cloud, no account, no telemetry: your agent's searches go straight to the sites you turned on. Public sites are on by default. Sites that need a login are off until you switch them on, and then they use the login already in your own browser; OmniSeek never sees your password. What it builds up as you use it stays in local files you own.
OmniSeek has no AI model of its own and sends nothing to a server of ours. Your agent does the thinking; OmniSeek goes and gets things. Settings: Configuration.
Tools
Your agent starts with omniseek_search; omniseek_sources shows what is available. The rest, from paper maps to saved searches and the notes your agent keeps (omniseek_ruling, omniseek_statement):
Tool | What it does |
| Search the whole catalog at once, remove duplicates, rank. Works across languages. |
| Turn any URL or document (web page, PDF, arXiv) into clean text. |
| Look at images, document figures, and video frames. |
| Transcribe audio or video locally, English and Chinese, from any timestamp. |
| Map a research field's citations: the papers it is built on and the recent ones. |
| Match a person's name to candidate author IDs across databases. |
| Map a researcher's collaborators by number of joint papers. |
| List who actively publishes at a lab, within a field. |
| Open-access PDF, retraction status, and citation count for a paper. |
| Similar papers (SPECTER embeddings) that keyword search misses. |
| Query the local graph of what OmniSeek has found: find, neighborhood, between, since, similar. |
| Saved searches that rerun on a schedule and report only what is new. |
| Record that two entries are (or are not) the same person or thing. |
| Record a directed relation between two entries. |
| Propose, test, add, or retire a source. |
| Read the queue of proposed sources or one source's report. |
| Run several tools in parallel, one response. |
| List sources by domain, region, capability, and health. |
One MCP prompt comes with them: investigate(target, shape, context), a ready-made investigation recipe, where shape is person, lab, field, product or chase and the optional context narrows the angle.
Every parameter, and what each returned field means: TOOLS.md. Each tool's own description ends by pointing at its section there.
More
Worked examples, real outputs · A full case study · FAQ, including how it differs from Exa and Tavily · All sources · Source health, updated weekly
How we test these claims: a test only counts if we first checked that plain web search could not find its answer on the first page (latest results). Using Claude Code? skills/omniseek-investigate is a ready-made research method: search wide, narrow in, add structure.
Contributing
See CONTRIBUTING.md: a new source has to find something plain web search doesn't. Fixing a source that stopped working is always welcome.
By participating you agree to the Code of Conduct.
Give your AI agent the parts of the internet web search doesn't reach.
Apache-2.0 · NOTICE · Security · Cite
Available Tools
18 toolsomniseek_coauthorsARead-only
Use WHEN you want WHO a researcher collaborates with: advisor + closest collaborators by joint-paper count, or how a paper's author group is connected (WebSearch cannot build this). One LAYER, not the whole graph: co-authorship is one edge type; the other layers, and what each tie means, are yours.
Tool name: omniseek_coauthors (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_coauthors".
Args: authors: names, ids (omniseek_resolve_identity) or "id1+id2" for one person split across ids. source: "openalex" (default) or "s2". hints: per-author disambiguation hints, parallel to authors. papers: per-author known papers, parallel to authors.
One author: their coauthors ranked by joint papers. Several: also the pairwise joint-paper edges among them and the bridge collaborators shared by two or more. Returns {source, n_authors, nodes: [{query, resolved, ambiguous, alternatives, works_seen, top_coauthors: [{id, name, joint}], degraded?}], edges: [{a, b, joint_count, papers}], bridges: [{id, name, shared_by, total_joint}], cooc: [{a, b, n}], degraded?}. degraded = the lookup failed: an empty graph is missing data to retry, not "no collaborators". More: omniseek docs/TOOLS.md, omniseek_coauthors.
Inputs: authors (required), hints, papers, source.
omniseek_curator_actA
Use WHEN acting on the source-curation protocol: WRITE a source-lifecycle action (submit / probe / decide / admit / retire ...); every safety gate lives in the impl, unchanged. Pick
the action with verb; the other arguments are that verb's:
submit (name, urls, mode, domain, family; optional kind, regions, rationale, draft): add a candidate; mode is STRUCTURE / UNWALL / TRANSCRIBE / RECALL / MONITOR.
probe (candidate_id): gather the evidence; returns the packet.
wall_probe (candidate_id): re-probe by rendering it in the isolated browser (a parked_p2 candidate, or one you judge a client-rendered shell).
decide (candidate_id, decision, reasons; baseline_ref to admit): admit / watch / reject. Refused: an admit with a hard red line, incomplete evidence, an empty baseline_ref or no packet.
apply_live (candidate_id): reversible live admit, rss-safe families only (others use stage_commit).
rollback_live (name, family): undo apply_live.
stage_commit (candidate_id): prepare the git commit text for a non-auto family; the operator commits.
retire_live (name; confirm): needs a PRUNE verdict; confirm=False previews, True writes a reversible override.
rollback_retire (name): undo retire_live.
source_verdict (name, verdict, rationale; prune_class, coverage_impact): KEEP / WATCH / PRUNE an existing source. Refused: a PRUNE its safety flags forbid.
Tool name: omniseek_curator_act (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_curator_act".
An unknown verb returns an error listing the valid values. Protocol: the /curator skill. More: omniseek docs/TOOLS.md, omniseek_curator_act.
Inputs: verb (required), kind, mode, name, +14 more.
omniseek_curator_viewARead-only
Use WHEN running the source-curation protocol (judge the admission queue or a source audit); READ curator state: queue | packet | audit. Never mutates. Pick a view with what:
what: "queue" (the admission backlog) | "packet" (the last evidence packet of a candidate, with the submitter's draft) | "audit" (per-source neutral audit facts and safety flags, no verdict).
candidate_id: the candidate, for what="packet".
state: filter for what="queue": new / probed / awaiting_verdict / admitted / watching / rejected / owner_review / redline_blocked / parked_p2 / error.
Tool name: omniseek_curator_view (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_curator_view".
An unknown what returns an error listing the valid values; a candidate with no packet yet returns {error} or {state}. Protocol: the /curator skill. More: omniseek docs/TOOLS.md, omniseek_curator_view.
Inputs: what (required), state, candidate_id.
omniseek_field_skeletonARead-only
Map a research field's shape: use WHEN you need its citation neighborhood (foundational core by citations vs frontier by date) to cluster yourself, from a topic or seed papers.
Tool name: omniseek_field_skeleton (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_field_skeleton".
Args: query: topic words; the top-relevance papers become the seeds. seeds: OpenAlex work ids you chose as anchors (preferred once you know the field). n_seeds: how many seeds to take from query. citers_per_seed: citing papers fetched per seed. source: "openalex" (default) or "s2" (Semantic Scholar: better arXiv coverage; nodes add influential, intent, contexts). max_nodes: node cap. fresh: bypass the cache. deadline_s: wall-clock cap (default about 25 s).
Returns {seeds, n_nodes, n_edges, edges: [[citer_id, cited_id]], nodes: [{id, title, year, date, cited_by, in_degree, concept, first_author, doi, url, is_seed, seed_ref_freq, seed_cite_freq}], _meta: {seed_titles, seed_note, degraded, deadline_hit, partial}}. in_degree = citations from inside the field; seed_ref_freq / seed_cite_freq on a non-seed node flag what your seeds miss. _meta.deadline_hit true = a partial map: retry or raise deadline_s. More: omniseek docs/TOOLS.md, omniseek_field_skeleton.
Inputs: fresh, query, seeds, source, +4 more.
omniseek_gatherARead-only
Run N independent read-only eye tools IN PARALLEL, returning results in one response.
Tool name: omniseek_gather (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_gather".
Args: calls: [{"tool": "omniseek_search", "args": {...}}, ...]: at most 10, read-only tools only; a call that needs another's result goes in a later gather. wait_s: return when all finish or after this many seconds; unfinished calls report status "warming" and keep running (collect later with staleness="cache_only", or repeat the same omniseek_transcribe).
Calls through one rate-gated upstream (several arXiv reads, say) run one after another at its pace; more than 2 search-index venues in one gather adds a warning. Returns {results: [{index, tool, status, result | error | hint}], elapsed_s, completed, warming, failed, total}; a wrong argument's hint names the tool's real parameters. More: omniseek docs/TOOLS.md, omniseek_gather.
Inputs: calls (required), wait_s.
omniseek_graphARead-only
Use WHEN you want HOW two entities connect, or what OmniSeek already knows AROUND a paper / author / entity; read-only, budgeted projections of its accumulated evidence graph with typed edges (ONE graph).
Tool name: omniseek_graph (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_graph".
Pass view and args (that view's own parameters); a call with no view lists the views and their parameters. Views return node ids, labels and edge tuples, never content. find {label_query, kind?}: the entry point, a name to candidate node ids. stats {}: counts by kind, type and tier. neighborhood {anchor, depth? (<= 2), types?, policy?, max_nodes?}: the subgraph around a node. between {a, b, types?, policy?, max_nodes?}: up to 8 shortest connection paths. voices {doc_ids (<= 64), policy?}: collapse documents to distinct upstream voices. since {anchor, date, types?, max_nodes?}: stored edges added after a date. similar {anchor (a doc), k?}: vector-nearest document candidates, proposals only. policy: conservative (exact-id identity only, default) | working (plus your omniseek_ruling rulings) | exploratory (plus fuzzy candidates). A cut result carries capped: true; a failure returns an error dict. Entity kinds fill in as calls happen, so early emptiness is normal. Record identity with omniseek_ruling, relations with omniseek_statement. More: omniseek docs/TOOLS.md, omniseek_graph.
Inputs: args, view.
omniseek_institution_cohortARead-only
Use WHEN you need the people-ROSTER of a lab / department / university (who actively publishes there, optionally scoped to a field): the "who's at this lab" question, orthogonal to co-authorship ("same lab, never co-authored" is still a tie, and co-authorship cannot see it).
Tool name: omniseek_institution_cohort (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_institution_cohort".
Args: institution: the lab, department or university. concept: the field to scope to ("machine learning", ...); without it you get the most prolific people across all fields. year_from: count works from this year on (biases to the current cohort). limit: how many people.
Returns {institution: {id, name}, filters, n, people: [{id, name, works_at_institution_in_field}], note}: a starting roster from OpenAlex, not a verified member list. More: omniseek docs/TOOLS.md, omniseek_institution_cohort.
Inputs: institution (required), limit, concept, year_from.
omniseek_paper_enrichARead-only
Use WHEN you need ONE paper's open-access full-text PDF, retraction / integrity status, or citation count: signals omniseek_search / field_skeleton do NOT give cleanly.
Tool name: omniseek_paper_enrich (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_paper_enrich".
Args: ids: DOIs and/or arXiv ids (not OpenAlex W-ids).
Returns {results: [{id, kind, doi, is_oa, oa_status, oa_by, pdf_url, oa_url, citation_count, integrity: {retracted, notices}}]}; an unrecognized id comes back as {id, error}. is_oa false = no free copy known to Unpaywall (still try omniseek_read on the DOI URL); retracted null = not checked; citation_count null = backend unreachable. Read pdf_url with omniseek_read for the full text. More: omniseek docs/TOOLS.md, omniseek_paper_enrich.
Inputs: ids (required).
omniseek_paper_recommendARead-only
Use WHEN you have a paper and want more like it: semantically-similar papers (SPECTER embeddings) that keyword search and the citation graph miss, including very recent work.
Tool name: omniseek_paper_recommend (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_paper_recommend".
Args: ids: seed paper ids: arXiv ids, DOIs or S2 ids (for an openalex hit, metadata.paper_id or metadata.doi, not the W-id). limit: how many papers.
Returns {seeds, n, papers: [{id, title, year, date, cited_by, first_author, doi, url}]} in S2 relevance order. More: omniseek docs/TOOLS.md, omniseek_paper_recommend.
Inputs: ids (required), limit.
omniseek_readARead-only
Read text from any URL OR document FILE: OmniSeek's single "read this deep" verb. AUTO-ROUTES.
Tool name: omniseek_read (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_read".
A local path, or a name ending in .pdf/.pptx/.docx/.xlsx/.txt/.md/.csv (and a local .html/.htm), goes to the document reader; anything else to the URL reader. arXiv /abs/ gives metadata, /pdf/ or /html/ the whole paper. A file from another machine goes into OmniSeek host's inbox ~/.omniseek/inbox first (or pass its URL).
Args: target: the URL or document path. start_char: where the returned window starts. max_chars: window size (default 24000); when truncated, re-call with start_char + returned_chars. level: "full" (default) | "brief" (title, author, abstract, size) | "head" (section list with char ranges) | "section". section: a section title (case-insensitive prefix) or index from level="head"; implies level="section". grep: a term, comma-separated terms or a list: return only the sentences that contain one, with one sentence of context. grep_word: grep matches whole words only. grep_case: grep matches case. export_media: (documents) export the embedded images. ocr: (documents) OCR every embedded image and append its text.
Returns (URL) {url, matched, total_chars, returned_chars, start_char, truncated, cached, fetched_at?, text_quality?, document, reason?}: matched false carries reason walled (drill the source by name with omniseek_search) | empty | blocked. Returns (document) {source, total_chars, returned_chars, start_char, truncated, cached, format, title, outline, media_total, media, media_dir, ocr_images?, text_quality?, text} or {source, error, inbox_files?}. text_quality (a PDF whose text layer reads as garbled): {level "low", readings, thresholds, hint}; read those pages with omniseek_view render_pages, and a term not found in that text may still be in the paper. With grep the body is replaced by grep: {terms, hits, occurrences, matches: [{start, end, text, terms}], returned_matches, truncated, next_start_char?}. An unknown section returns error and available_sections. To see figures use omniseek_view. More: omniseek docs/TOOLS.md, omniseek_read.
Inputs: target (required), ocr, grep, level, +6 more.
omniseek_resolve_identityARead-only
Resolve a PERSON's name to candidate author ids: the shared front door for EVERY relationship tool. It never picks: it returns ranked candidates for you to disambiguate.
Tool name: omniseek_resolve_identity (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_resolve_identity".
Args: name: the person's name. hint: an institution or field; only re-orders candidates. source: "auto" (OpenAlex, plus Semantic Scholar when the top hit is sparse), "openalex" or "s2". paper: arXiv id / DOI / title of a known paper by this person; pins a common-name junior.
Returns {query, source, candidates: [{id, source, name, works_count, cited_by, institution, via_paper?}], ambiguous, note, likely_same_person?: [{source, ids, name, merge_token, note}], degraded?}. ambiguous true = confirm with a hint, a paper or a known coauthor. merge_token ("A1+A2") goes straight into omniseek_coauthors. degraded = the OpenAlex lookup failed, so an empty result is missing data: retry, or pass source="s2" or paper=. More: omniseek docs/TOOLS.md, omniseek_resolve_identity.
Inputs: name (required), hint, paper, source.
omniseek_rulingA
Use WHEN two graph nodes ARE (or are NOT) the same person / entity and you want views to collapse them: record / list / retract same_as | not_same_as rulings (the one judgment channel the graph's working policy applies).
Tool name: omniseek_ruling (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_ruling".
create (src, dst, verdict "same" | "not_same"; optional note): returns {created, ruling, replaced}; the unordered pair is the key, so re-creating replaces it. list: {rulings: [{src, dst, verdict, note, ruled_at}], count}. delete (src, dst): {deleted}. omniseek_graph applies rulings under its working and exploratory policies; not_same beats same. A bad verdict, empty or identical endpoints, or an unknown action return {error}. More: omniseek docs/TOOLS.md, omniseek_ruling.
Inputs: action (required), dst, src, note, +1 more.
omniseek_searchARead-only
Search the curated sources. The default for "best/latest on X". ONE verb, three shapes.
Tool name: omniseek_search (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_search".
Shapes: default = one ranked, deduped, cross-lingual list; raw=True with exactly one source = an unbounded drill of that source (the way to reach walled or slow sources, which the broad sweep drops at its deadline); raw=True otherwise = uncollapsed per-source buckets.
Args: query: search words; empty browses by recency. sources: source names (None = every non-explicit_only source); take names from omniseek_sources. limit: max documents (per source in buckets). semantic: None = lexical plus vector recall; False = exact tokens only; True = lean on vectors. raw: see shapes. full: whole content per document. wait_s: patience budget in seconds (None = default deadline). staleness: "fresh" (bypass cache) | "cached_ok" (default) | "cache_only" (read what already warmed, send nothing). debug: keep the ranking telemetry in each document's metadata. filters: dict ({"year": {"gte": 2020}}) or expressions ("k=v", "k=a,b", "k>=n", "k=a..b", "k~text"); fields per source in omniseek_sources. as_of: "YYYY-MM-DD" or an ISO time with zone: only items that existed then.
Fire then collect: call with a small wait_s, then again ~20 s later with staleness="cache_only", the SAME query and the SAME limit (limit is in the cache key): faster and more complete.
Returns {query, count, documents, _meta, routing_hint?} (ranked); {source, query, count, documents, _meta?} (one-source drill: _meta.diagnostic when empty or errored, _meta.held when the eye's own gate sent nothing); {query, results: {source: [...]}, total_count, _meta} (buckets). _meta names timed_out / empty / errored / held sources (held = not tried, says nothing about the topic) and excluded_relevant walled sources worth naming. A bad filter returns error, filter_problems and available_filters and sends nothing; a bad as_of returns error. When _meta.web_search_backend shows cooling, wait cooling_s before retrying. More: omniseek docs/TOOLS.md, omniseek_search.
Inputs: query (required), raw, full, as_of, +7 more.
omniseek_sensorA
Use WHEN you want to MONITOR a query over time and be told only what's NEW: standing queries with novelty detection. ONE verb; action picks what to do.
Tool name: omniseek_sensor (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_sensor".
create (query; optional sources, schedule hourly | daily | weekly, notify, notify_if, notify_if_match "any" | "all", detect_absence, notify_source): register a sensor; returns it with its id (and schedule_note when the deployment needs a SERVICES.tsv row to run it). update (sensor_id, notify_source): change its push source ("" = default); returns {updated, sensor}. list: all sensors with last-run stats. delete (sensor_id): returns {deleted}. run (sensor_id): run it now; returns new_count and new_titles. notify=True pushes new results of scheduled runs (notify_if narrows that to keyword matches); detect_absence also alerts when a tracked stable-source item disappears. An unknown action or a missing required argument returns {error}. More: omniseek docs/TOOLS.md, omniseek_sensor.
Inputs: action (required), query, notify, sources, +6 more.
omniseek_sourcesARead-only
List all sources: call this to ROUTE before searching.
Tool name: omniseek_sources (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_sources".
A bare call returns the routing vocabulary and the bare inventory, not every source's facets.
Args: domain: only sources whose domains facet has it ("jobs", "papers", ...), with descriptions. query: sources ranked by token overlap with these words (English and Chinese), with descriptions. region: only sources whose regions facet has it ("sg", "ca", "cn", ...). verbose: every source with its full facets and description. field: with a query/domain that picks one source, also return that filter field's known values. check_health: probe every source live (slow) and add a system block.
Returns {count, backend_count, backend_breakdown} plus either the bare orient {source_names, available_domains, available_regions, capabilities, note} or sources: [{name, backend, description, needs_credentials, explicit_only, explicit_only_reason?, param_hint?, stability, access_tier, health, kind?, domains?, regions?, modes?, filters?, coverage?, license?, samples?, as_of_field?}]. backend_count counts distinct upstreams (count over-states coverage). health: ok | down | unmeasured | unverified | unknown | sealed; with check_health, healthy null means not verified, neither working nor failed. A near-miss domain or region returns did_you_mean. More: omniseek docs/TOOLS.md, omniseek_sources.
Inputs: field, query, domain, region, +2 more.
omniseek_statementA
Use WHEN you've concluded a DIRECTED, decision-relevant relation OmniSeek does NOT already store mechanically (X acquired_by Y, paper P refutes claim Q, path R requires gate S) and want the graph to carry it forward: record / list / retract typed relation statements (the general sibling of omniseek_ruling; identity types belong to omniseek_ruling).
Tool name: omniseek_statement (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_statement".
Record one only when all three hold: OmniSeek does not already store it (cites, authored, affiliated and the like are mechanical), it would change a future decision, and a point-in-time relation carries its as-of date in the note. Prose conclusions belong in notes, not here. create (src, dst, type, note; optional doc): type is free vocabulary, slugged to [a-z0-9_], at most 40 characters; note (your reasoning) is required; doc is a provenance node id. Returns {created, statement, replaced, similar_anchors?}: reuse a hand-minted id from similar_anchors instead of minting a near-duplicate. (src, dst, type) is the key; re-creating replaces it. list (optional about, type): {statements, count}, at most 200 (capped flag). delete (src, dst, type): {deleted}. Shown by omniseek_graph under working and exploratory, and on later omniseek_search hits of an endpoint. Refused with {error}: type same_as / not_same_as (use omniseek_ruling), a bad type, an empty endpoint or note, an unknown action. More: omniseek docs/TOOLS.md, omniseek_statement.
Inputs: action (required), doc, dst, src, +3 more.
omniseek_transcribeARead-only
Transcribe the SPOKEN content of a video / podcast / audio URL via local SenseVoice ASR (bilibili, xiaoyuzhou, direct audio). YouTube captions come from omniseek_read instead.
Tool name: omniseek_transcribe (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_transcribe".
Slow on the first call for a long item, then cached. For a long episode take the chapter from the shownotes and transcribe only that slice.
Args: url: the video, podcast or audio URL. language: "" auto-detects; "zh" / "en" skip detection. start: slice start, seconds or MM:SS / HH:MM:SS. duration: slice length, same forms. segments: also return [{start, end, text}] per segment (an extra pass). diarize: who said what: segments carry speaker labels (Chinese-focused, heavier; supersedes segments). speakers: known speaker count for diarize (0 = auto; pass it when you know it).
Returns {url, transcript, chars, audio_seconds, asr_seconds, source, title, cached, start_seconds?, duration_seconds?, segments?, speakers?}, or {url, error, transcript: ""} when no audio resolved. Repeating the same call while it runs attaches to that run; still running gives {status: "running", already_running: true, running_seconds, phase, note}: call again later. Over the machine's transcription limit it is queued and runs without you: {status: "queued", queue_position, note}; call again later with the same arguments. More: omniseek docs/TOOLS.md, omniseek_transcribe.
Inputs: url (required), start, diarize, duration, +3 more.
omniseek_viewARead-only
SEE with your own vision, IN-BAND: document figures, loose image URLs, or video frames.
Tool name: omniseek_view (your MCP config adds its own prefix; never guess one). Not in your tool list? ToolSearch "omniseek_view".
kind="auto" sends a document path or extension to document figures, a video URL (youtube, bilibili, douyin, .mp4/.webm/.mov) to frames, anything else to image URLs.
Args: target: document path or URL, video URL, or image URLs separated by commas, spaces or newlines. kind: "auto" | "document" | "images" | "video". sections: (document) slide or page numbers, comma-separated; "" = all. names: (document) exact image names from omniseek_read's outline media[].name. render_pages: (PDF) whole pages to render, for vector figures and tables with no embedded image. max_images: full-resolution cap; a wider selection comes back as a contact sheet. contact_sheet: (document) always return one tiled contact sheet. start: (video) slice start, e.g. "8:30" or "90". duration: (video) slice length; default the whole video, capped at 30 minutes. n: (video) frames to sample (default 12, max 24).
Returns image blocks: a contact sheet with a legend, or a manifest plus one block per image; or an error or "nothing to show" note. Usual flow: omniseek_read for the outline, this with no selection for a contact sheet, then the figures that matter by sections or names. More: omniseek docs/TOOLS.md, omniseek_view.
Inputs: target (required), n, kind, names, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools have clearly distinct targets: search/read/view/transcribe for content access, sensor for monitoring, curator_view/curator_act for read/write curation, and graph/ruling/statement for knowledge-graph operations. Some boundaries require careful reading — search vs paper_recommend vs field_skeleton, read vs view, and graph vs field_skeleton — but the descriptions generally clarify when to use each.
All names use the same omniseek_ prefix and lowercase snake_case, which is predictable and readable. However, the set mixes noun names (sources, sensor, graph, statement), verb names (search, read, transcribe, gather), and inconsistent compound patterns (paper_recommend/enrich vs resolve_identity, curator_view/act).
Eighteen tools is heavy for a single server and sits in the borderline 16–25 range, especially with many specialized sub-areas. The ambitious research/discovery/curation scope justifies the breadth, but the surface still feels large enough to burden tool selection.
The surface broadly covers discovery, reading, media transcription/vision, paper enrichment/recommendation, people and institution lookup, monitoring, graph reads/writes, and curation lifecycle. Minor workflow gaps may remain, but most core research tasks have a follow-through path rather than an obvious dead end.
Maintenance
Related MCP Connectors
An MCP memory server. One memory your agents share — across models, devices and apps.
Search engine for AI agents to find MCP servers, A2A agents, and skills on their own.
One MCP for any agent: your connected apps, shared memory, web search, social data and media tools.
Web search API and MCP server for developers building AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server giving AI agents real-time web search, page scraping, company intelligence, email discovery, local lead generation, and a persistent knowledge graph. Pay only for what you use, no subscriptions.MIT

Augentofficial
AlicenseBqualityDmaintenanceMCP server that turns any audio or video source into structured, searchable intelligence for agents, enabling download, transcription, semantic search, speaker identification, and more.226MIT- AlicenseNot gradedqualityBmaintenanceA private, self-hosted MCP server that wraps a retrieval pipeline over your own data, enabling trusted AI agents to access and manage your personal memory through standard MCP tools.Apache 2.0
- AlicenseNot gradedqualityAmaintenanceMCP server that enables AI agents to watch and analyze videos from 1800+ sources, with persistent indexing, OCR, transcription, and a self-verification loop for debugging.MIT