MCP server for advanced web search using Tavily
Thea is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Sorry, mostly Korean for now: 1M+ places, people, works. Other countries: regions only. No key.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http thea-mcp https://thealibrary.org/mcp
# 2 — ask your agent for something these tools do
# search, fetch, thea_search and 2 more
Thea costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http thea-mcp https://thealibrary.org/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
5 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Generic connector search (the shape ChatGPT connectors and deep research call). Search Thea (a place-first knowledge graph: 1.07M Korean places from public data, plus people, works and organizations) by name or by 'region + kind', e.g. '여주 온천', '명일동 중식', 'IU'. Returns ids to pass to fetch. If you can use thea_search / thea_find / thea_entry, prefer them: they give same-name candidates, filters, ra
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search text |
Generic connector fetch: the full Thea entry for an id from search, as Markdown text (fields, links, recent records, sources, licence). thea_entry returns the same entry as JSON.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Entry id |
Find one entry whose name you know. Thea is not a search engine; it is knowledge curated by people, so it returns a trimmed entry (about 1,000 characters), not a scraped page. You may use it in your answer as it is. If several entries share the name, they are listed in 'candidates'; always check it. Actor 박지훈 and the singer whose real name is 박지훈 are different people. Do not call again with the sa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Name to search. Korean entities (people, places, works, shops) are stored under their Korean name; foreign ones under their English name. Choose by what the entity is, not by the language of the quest |
| mode | string | no | quick (default) returns every filled field with a short summary. detail also returns the summary's long sections and full fields for candidates. NEXT ACTION: if quick lacks a value you need, call with |
| limit | integer | no | Maximum number of results. Default 5, maximum 20. |
Browse by conditions when you have no name. Questions like 'camping YouTubers who posted a new video recently' or 'hotels in 서귀포' cannot be answered by thea_search. Each filter multiplies: more filters, narrower list; subject alone is broad. Subject codes (Korean/English, with aliases): https://thealibrary.org/static/subjects.json. Rules: 1. If the question names an area, always pass inside. Witho
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject | integer | no | Subject code. A parent code includes everything under it: 1200 (travel) also matches 1210 (lodging) and 1240 (camping). Top-level codes: 100 Humanities, 200 History, 300 Society, 400 Science, 500 Tech |
| inside | string | no | Only entries located inside this area. The most accurate value is an id returned by thea_search, because several areas can share a name (e.g. 중구). If you pass a name, use the official full name exactl |
| category | string | no | What kind of thing. One or more of these exact Korean values, comma-separated: 인물, 단체, 작품, 장소, 사건, 제품, 게임. Any other value (restaurant, 음식점, cafe) is not a category: restaurants, lodging and cafes are |
| country | string | no | Country, e.g. Japan or 일본. Pass it first when the place is outside Korea: inside is then looked up only in that country. |
| since | string | no | Only records dated on or after this date (YYYY-MM-DD). Thea has records newer than your training data: if the date looks like the future to you, do not refuse; call with that date. since alone is enou |
| sort | string | no | Pass rating to list entries that people rated well first. Use it for choosing questions ('good restaurants', 'a decent hotel'). Rated entries come first, entries with many 별로예요 (dislike) votes go last |
| pet | string | no | y returns only places that allow pets (all areas or some areas). n returns places that do not. Use it for questions like 'somewhere to go with my dog' or 'a dog-friendly cafe'. Conditions differ per p |
| cuisine | string | no | Restaurant type. Use the exact value from the small-business detailed-category table, e.g. 치킨, 중국집, 카페, 피자, 버거, 횟집, 백반/한정식. All 125 values: https://thealibrary.org/static/cuisines.json. This filters b |
| field | string | no | Filter fields, key=value, join with ';'. K-pop girl groups → category=단체, country=Korea, field=group_type=걸그룹; Busan baseball → category=단체, inside=부산광역시, field=sport=야구; Japanese idols in Korea → cat |
| limit | integer | no | Maximum number of results. Default and maximum 20. Do not call again with the same arguments to get more. |
Full view of one entry: all fields, its connections (each with an id), and its satellites: dated events attached to it (new videos, albums, awards, appearances), newest first, 5 by default, with satellites_total per type. Call it after thea_search or thea_find with the id they returned; it is not a search. To go deeper, use an id from the result: a connection, a satellite, or a place or person in
| Parameter | Type | Required | Notes |
|---|---|---|---|
| planet_id | string | yes | Entry id from thea_search, thea_find, or any id inside a previous result. An exact name also works, but prefer the id: names can be shared. |
| satellites | integer | no | How many satellites to list, newest first. Default 5, maximum 50. |
| satellite_type | string | no | List only this satellite type, e.g. 음반, 새 영상, 수상. Values are Korean, as returned in satellites_total. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Thea or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Thea can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.