MCP server for advanced web search using Tavily
Nothing to run from here
AgentWeb 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.
93/100
tool-list score
37
tools declared
remote
at its publisher
—
calls last 7d
What it does
Free web search, 130M+ business records, local search, weather and travel data for AI agents.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agentweb-agentweb-mcp https://api.agentweb.live/mcp --header 'X-API-Key: ${X_API_KEY}'
# 2 — ask your agent for something these tools do
# search_businesses, local_search, get_business and 34 more
It needs X_API_KEY (Get a free API key at https://agentweb.live/#signup. No credit card required): this sends it in the X-API-Key header from your environment, so export it first — its endpoint answers 401 without it.
AgentWeb costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AGAll 2 servers
agentweb2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
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.
Claude Codedeclared by this listing
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 Code reads X_API_KEY (Get a free API key at https://agentweb.live/#signup. No credit card required) from your environment each time it connects and sends it in the X-API-Key header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx X_API_KEY … and open a new terminal (Windows).
claude mcp add --scope user --transport http agentweb-agentweb-mcp https://api.agentweb.live/mcp --header 'X-API-Key: ${X_API_KEY}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: X-API-Key header — Get a free API key at https://agentweb.live/#signup. No credit card required.. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
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.
What you approve
37 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.
Search the AgentWeb global business directory. Use agentweb_health for current counts. If a business is not in the database yet, AgentWeb tries to discover it from the web in real time (~3s) and saves it. Returns markdown prose by default. Supports text search (q), category, city/country, and geographic search (lat+lng+radius_km). ONE CALL RETURNS EVERYTHING: name, phone, email, hours, website, ad
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | no | Text search query, e.g. 'noma', 'thai restaurant', 'dentist near me' |
| category | string | no | Business category filter (e.g., 'restaurant', 'hotel', 'pharmacy') |
| city | string | no | City name for location filter |
| country | string | no | Country code (ISO 3166-1 alpha-2, e.g., 'US', 'GB', 'DK') |
| lat | number | no | Latitude for geographic search (requires lng and radius_km) |
| lng | number | no | Longitude for geographic search (requires lat and radius_km) |
| radius_km | number | no | Search radius in kilometers (used with lat/lng) |
| limit | number | no | Maximum number of results (default: 10, max: 100) |
| cursor | string | no | Pagination cursor from a previous response's meta.next_cursor |
| format | string | no | Response format. 'text' (default) returns markdown prose; 'json' returns structured JSON. |
Search local businesses from external sources; availability and freshness vary. Returns name, star rating, review count, phone, today's opening hours, website, full address, category, and geo coordinates for each result. Use when you need CURRENT info (today's hours, latest ratings) or when search_businesses doesn't have the business yet. Use for location-based business queries. Results may be cac
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | What to look for, e.g. 'coffee shops', 'dentist', 'thai restaurant' |
| location | string | no | City, area, or 'near me': e.g. 'Copenhagen', 'Shibuya Tokyo' |
| limit | number | no | Maximum number of results (default: 15) |
Fetch a single business by slug or UUID. Returns markdown prose by default (~60% fewer tokens than JSON). Slugs look like 'noma-copenhagen-abc12345'. Use when you already have an identifier from a previous search. Set format='json' for structured data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Business slug (e.g. 'noma-copenhagen-abc12345') or UUID. Slugs preferred. |
| format | string | no | 'text' (default) markdown prose; 'json' structured JSON. |
Fetch a business in the AgentWeb compact shorthand format (~320 bytes vs 3-5 KB). Single-letter keys (n=name, p=phone, e=email, w=website, h=hours, g=[lat,lng]…). ~80% fewer tokens. Use when you just need contact info. Schema: https://api.agentweb.live/v1/schema/short
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | The unique business ID from AgentWeb |
Check the health status of the AgentWeb API, including total businesses and countries available.
No parameter schema on file.
Get the machine-readable description of the entire AgentWeb API: every endpoint, tool, data source, and current live counts. Use to discover what AgentWeb can do.
No parameter schema on file.
Contribute a new business to AgentWeb, OR enrich an existing one with missing data (phone, email, website, hours, address). Deduplicates automatically: same name within 100m, or a matching phone, merges into the existing record. Use whenever you find structured business data AgentWeb doesn't have yet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Business name (required, min 2 chars) |
| phone | string | no | Phone number (any format; will be cleaned) |
| website | string | no | Business website URL |
| string | no | Business email address | |
| category | string | no | Business category, e.g. 'restaurant', 'dentist', 'hotel' |
| country_code | string | no | ISO 3166-1 alpha-2 country code, e.g. 'US', 'DE' |
| lat | number | no | Latitude (recommended for accurate dedup) |
| lng | number | no | Longitude (recommended for accurate dedup) |
| address | object | no | Address fields: { street, city, postcode, country, full } |
| hours | object | no | Opening hours (e.g. { monday: '09:00-17:00', ... }) |
Report a business as closed, having wrong info, or being spam. Three or more 'closed' reports automatically lower its confidence score. Use when you discover a business is permanently closed, has wrong phone/address/hours, is spam, or is a duplicate.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| business_id | string | yes | The unique business ID from AgentWeb (required) |
| report_type | string | yes | Type of issue |
| details | string | no | Optional free-text explanation, max 500 chars |
Get the public leaderboard of top contributing AI agents (most creates, enrichments, reports).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Number of top contributors (default: 10, max: 50) |
Autocomplete / type-ahead for business names, cities, or categories. Use to disambiguate user input before searching. Returns up to 15 suggestions by relevance. Fast (<20ms).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Query prefix, min 2 characters (e.g. 'nom', 'copenh') |
| type | string | no | What to autocomplete (default: 'business'). |
| country | string | no | Optional ISO country code to narrow suggestions |
| limit | number | no | Max suggestions (default: 10, max: 15) |
Fetch up to 50 businesses in a single call by IDs or slugs. Saves N round-trips. Supports prose (markdown), JSON, and shorthand formats.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ids | string | yes | Comma-separated business IDs or slugs (max 50) |
| format | string | no | 'text' (default) markdown; 'json' structured; 'short' compact shorthand. |
Get the most searched/popular businesses on AgentWeb right now (last 24h or all time).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| period | string | no | Time period (default: '24h'). |
| limit | integer | no | Max results (default: 10) |
Retrieve this agent's interaction history: every business it searched for, viewed, or contributed to. Persists 90 days, up to 500 interactions. Recall past lookups without re-searching.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max entries (default: 50, max: 500) |
| offset | number | no | Skip N entries (default: 0) |
Get this agent's implicit favorites: businesses it interacted with more than once, by frequency.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max favorites (default: 20, max: 100) |
Get this agent's identity and stats: API key info, tier, contribution count, request totals, remembered interactions.
No parameter schema on file.
Search flights across multiple sources (booking.com + kiwi.com) and return the cheapest. Returns airlines, prices, times, stops, duration, source, and booking links. ~3s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Origin airport IATA code (e.g. 'CPH', 'JFK', 'LHR') |
| to | string | yes | Destination airport IATA code (e.g. 'FCO', 'CDG', 'NRT') |
| depart | string | yes | Departure date YYYY-MM-DD |
| return | string | no | Return date YYYY-MM-DD (omit for one-way) |
| adults | number | no | Adult passengers (default: 2) |
| cabin | string | no | Cabin class (default: ECONOMY) |
| sort | string | no | Sort order |
| limit | number | no | Max results (default: 10) |
Search hotels across multiple sources (booking.com + kiwi.com) and return the cheapest. Returns name, price, stars, rating, reviews, source, booking links. ~2s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| destination | string | yes | City or destination (e.g. 'Rome', 'Tokyo') |
| checkin | string | yes | Check-in date YYYY-MM-DD |
| checkout | string | yes | Check-out date YYYY-MM-DD |
| adults | number | no | Adult guests (default: 2) |
| sort | string | no | Sort by price |
| max_price | number | no | Maximum price per night filter |
| limit | number | no | Max results (default: 10) |
Search real-time car rental availability and prices on booking.com via AgentWeb. Returns vehicle, supplier (Avis, Hertz, Sixt…), price, transmission, doors, mileage, pickup location, booking links. Works with any airport IATA code. ~1s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| location | string | yes | Pickup: airport IATA code or city name |
| pickup_date | string | yes | Pickup date YYYY-MM-DD |
| dropoff_date | string | yes | Drop-off date YYYY-MM-DD |
| dropoff | string | no | Drop-off location if different from pickup |
| pickup_time | string | no | Pickup time HH:MM (default: 10:00) |
| dropoff_time | string | no | Drop-off time HH:MM (default: 10:00) |
| driver_age | number | no | Driver age (default: 30) |
| transmission | string | no | Filter by transmission type |
| sort | string | no | Sort by price |
| limit | number | no | Max results (default: 15) |
Search flights on Kiwi.com: aggregates all airlines, often cheaper than airline sites. Returns prices, airlines, times, stops, duration, booking links. ~1.5s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Origin airport IATA code |
| to | string | yes | Destination airport IATA code |
| depart | string | yes | Departure date YYYY-MM-DD |
| return | string | no | Return date YYYY-MM-DD (omit for one-way) |
| adults | number | no | Adult passengers (default: 1) |
| cabin | string | no | Cabin class (default: ECONOMY) |
| sort | string | no | Sort (default: price) |
| limit | number | no | Max results (default: 10) |
Search FlixBus bus and train routes between cities in Europe. Returns prices, times, duration, transfers, booking links. ~1s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Origin city (e.g. 'Copenhagen', 'Berlin') |
| to | string | yes | Destination city (e.g. 'Berlin', 'Rome') |
| date | string | yes | Travel date YYYY-MM-DD |
| adults | number | no | Passengers (default: 1) |
| sort | string | no | Sort (default: cheapest) |
| limit | number | no | Max results (default: 10) |
Convert between currencies using live ECB exchange rates. 30+ currencies. Returns converted amount and rate. ~0.5s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | yes | Amount to convert |
| from | string | yes | Source currency code (e.g. 'USD', 'EUR') |
| to | string | yes | Target currency code (e.g. 'EUR', 'JPY') |
Get the current date and time in a country (e.g. Denmark), supported city, or IANA timezone. Returns UTC offset, DST, Unix timestamp and timezone-data version. Fresh every call. Countries with multiple zones return choices; select one and retry. Use this for 'What time is it in Denmark right now?'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| location | string | no | Country name/code or supported city, e.g. Denmark, DK, Tokyo. Use either location or timezone. |
| timezone | string | no | IANA timezone, e.g. Europe/Copenhagen. Defaults to UTC if neither field is supplied. |
Convert a local date/time between IANA zones, supported cities or countries. Rejects nonexistent clock-change times. Repeated local times require fold=0/1 or an explicit UTC offset. HH:MM uses today's date in the source zone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Source IANA timezone, supported city or country. |
| to | string | yes | Destination IANA timezone, supported city or country. |
| time | string | no | ISO datetime, YYYY-MM-DD HH:MM, HH:MM or now (default). |
| fold | integer | no | First (0) or second (1) occurrence during a backward clock change. |
Get weather forecast for any city worldwide. Returns current conditions plus daily forecast up to 14 days (high/low, rain chance, UV, sunrise/sunset, packing advisories). ~1s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | yes | City name (e.g. 'Rome', 'Tokyo', 'New York') |
| days | number | no | Forecast days (1-14, default: 3) |
| units | string | no | Temperature unit (default: celsius) |
Search real-time attractions, tours, and activities on booking.com via AgentWeb. Returns name, price, description, rating, duration, free-cancellation, discounts, booking links. ~2s.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| destination | string | yes | City name (e.g. 'Rome', 'Tokyo', 'Barcelona') |
| date | string | yes | Date YYYY-MM-DD |
| end_date | string | no | End date YYYY-MM-DD (defaults to date) |
| sort | string | no | Sort (default: popular) |
| limit | number | no | Max results (default: 15) |
Discover every public recipe and its parameters, authentication and cache policy. Includes news, holidays, Wikipedia, Amazon products and provider-specific travel. A listed recipe is not a guarantee of upstream availability.
No parameter schema on file.
Execute a public recipe discovered with list_recipes. Pass its exact domain, recipe_name and named params. Covers all public recipes, including those without a dedicated tool. Upstream errors are returned as tool errors. Authentication follows the selected recipe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Catalog key, e.g. news, holidays, wikipedia.org or amazon.com |
| recipe_name | string | yes | Recipe name, e.g. search, list or search_products |
| params | object | yes | Named parameters from list_recipes. Do not include authentication credentials. |
General web search. mode=index searches AgentWeb's own indexed pages with a short time budget; mode=hybrid also queries external sources (the default). Returns the top web results (title, URL, snippet) for a query: general web pages, not just businesses. Use for research, finding pages, and current info. Pair with web_fetch to read a result.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Search query |
| num | integer | no | Number of results (default 10, max 20) |
| mode | string | no | — |
Web search PLUS the cleaned text of the top pages in one call (pages are fetched in parallel). Prefer this over web_search + web_fetch whenever you need to read the results, not just list them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Search query |
| num | integer | no | Pages to read (default 3) |
| max_chars | integer | no | Characters per page (default 2500) |
| idempotency_key | string | no | Reuse for a retry of exactly the same operation/input. |
| max_duration_ms | integer | no | — |
| max_units | integer | no | — |
| intent | string | no | — |
| entity | string | no | Explicit entity for official_website candidate identification; ownership is not verified. |
Page fetch. Fetches a public URL and returns its cleaned text content (title + body) ready to read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The page URL to fetch |
| max_chars | number | no | Truncate content (default 8000) |
Retrieve an exact evidence passage and its immutable capture metadata. Evidence is scoped to this application's user/workspace and retained for seven days.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| evidence_id | string | yes | — |
Get the status, evidence and usage receipt of an accepted research request.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request_id | string | yes | — |
Request cancellation of an accepted research execution. In-flight usage can remain pending; retrying cancellation does not start new work.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| request_id | string | yes | — |
Create an expiring, resource-limited watch for URL text changes, text appearance or an unambiguous structured product price. Baselines are silent by default. An optional webhook receives signed changes; without it, poll watch_events.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | no | — | |
| query | no | — | |
| kind | string | yes | — |
| terms | array | no | — |
| price | no | — | |
| currency | no | — | |
| interval_seconds | integer | no | — |
| expires_in_seconds | integer | no | — |
| max_checks | integer | no | — |
| max_units | integer | no | — |
| max_pages | integer | no | — |
| notify_initial | boolean | no | — |
| webhook_url | no | — | |
| idempotency_key | string | no | Reuse for a retry of exactly the same operation/input. |
List change watches in the current application/user/workspace scope.
No parameter schema on file.
Read detected changes, supporting evidence and delivery status for a watch in the current scope.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| watch_id | string | yes | — |
| after | string | no | next_cursor from the previous page |
Cancel a watch and its queued callback deliveries. An already in-flight delivery may still arrive.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| watch_id | string | yes | — |
Free
$0 forever
- 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 AgentWeb or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.21.1 · scanned 30 Oct 2026
Graded from the tools this server lists, not from its source code.
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.
Threat score100
Client score93
Findings0 threat · 4 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digeste4fd54d0652c746341d7c40cc9ed06712b99e28f8176bd0aa3d2e41fbecf22a8
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_businesses | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| local_search | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_business | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| agentweb_get_short | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| agentweb_health | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| agentweb_capabilities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| contribute_business | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| report_business | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| agentweb_leaderboard | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| suggest | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| batch_get_businesses | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| trending_businesses | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| agent_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| agent_favorites | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| agent_profile | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_flights | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_hotels | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_cars | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwi_search_flights | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| flixbus_search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| currency_convert | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| time_now | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| time_convert | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| weather_forecast | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_attractions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_recipes | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| execute_recipe | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| web_search | untrusted-input | untrusted-input: keyword "web_search", declares openWorldHint: true (interacts with entities outside the server) |
| web_research | untrusted-inputexternal-sink | untrusted-input: keyword "web_search"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| web_fetch | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| evidence_get | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| research_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| research_cancel | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| watch_create | external-sink | external-sink: keyword "webhook", parameter "webhook", declares readOnlyHint: false, openWorldHint: true |
| watch_list | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| watch_events | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| watch_cancel | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digeste4fd54d0652c7463
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
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 1.21.1.
1.21.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish AgentWeb can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.