Search, save and rate AI tools people shared in chats. Local catalogue, any model or none.
Nothing to run from here
Agentwebmap 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
20
tools declared
remote
at its publisher
—
calls last 7d
What it does
Find publisher documentation via llms.txt, with source links, evidence and check dates.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agentwebmap-mcp https://agentwebmap.com/mcp
# 2 — ask your agent for something these tools do
# resolve, watch_domain, unwatch_domain and 17 more
Agentwebmap 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 1 server
agentwebmap1 server
1 category
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 mcp add --scope user --transport http agentwebmap-mcp https://agentwebmap.com/mcpReconnect, 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.
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
20 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.
Start here to find documentation for a domain or development task. Returns specific page URLs with publisher excerpts, matching evidence, owner-stated terms, freshness and alternatives. Task relevance ranks ahead of ownership verification. Weak matches are fallback candidates: refine the query or search elsewhere. Use max_age to mark stale data, refresh to validate the source live, and detail=full
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | A domain or development task, e.g. "modelcontextprotocol authorization". |
| detail | string | no | Compact consumer fields by default; full adds owner profile, claims and listing metadata. |
| category | string | no | Filter by inferred topic ID from list_categories. Topics describe publisher metadata, not capabilities or correctness. |
| capability | string | no | Filter to sites explicitly publishing an MCP endpoint link. Publisher declaration alone does not prove availability. |
| max_age | integer | no | Maximum acceptable age of source health in seconds; stale data is marked, not hidden. |
| refresh | boolean | no | Validate the selected source live (bounded and rate limited); does not change the directory listing. |
| limit | integer | no | Maximum number of documentation sources. |
Subscribe to a domain: a signed JSON POST goes to your webhook when its llms.txt changes, breaks, is restored, loses its llms-full.txt, changes tier, or its verification changes. Returns a watch id and a secret (shown once) for the signature and for unsubscribing. 20 new watches per hour per client, 5 active per domain per client.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| webhook_url | string | yes | Public http(s) URL that accepts a JSON POST. |
Cancel a watch with its id and secret.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| watch_id | integer | yes | — |
| secret | string | yes | — |
Send a test event to a watch's webhook (once per 10 minutes).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| watch_id | integer | yes | — |
| secret | string | yes | — |
Directory-wide counts for Agent Web Map: domains tracked, valid llms.txt files, listed, verified, pending.
No parameter schema on file.
List the topic taxonomy and counts of featured/listed sites by inferred category, unclassified sites and publisher-declared MCP endpoints. Categories describe topics; capabilities are separate explicit publisher declarations. Counts can overlap. Use category or capability filters with resolve, search_llms_registry or list_domains. An MCP declaration does not prove availability.
No parameter schema on file.
Search domains and indexed documentation links by development task. Text relevance ranks before authority and ownership verification. Compact results omit owner claims by default; use detail=full for profile metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search terms, e.g. "payments api docs". |
| page | integer | no | — |
| per_page | integer | no | — |
| verified_only | boolean | no | Only domains whose owner has verified them. |
| include_unlisted | boolean | no | Also return low-authority (unlisted) entries. |
| detail | string | no | Compact consumer fields by default; full adds owner profile, claims and listing metadata. |
| category | string | no | Filter by inferred topic ID from list_categories. Topics describe publisher metadata, not capabilities or correctness. |
| capability | string | no | Filter to sites explicitly publishing an MCP endpoint link. Publisher declaration alone does not prove availability. |
Ranked listing of the directory (verified first, then authority). Use verified_only to get only owner-verified sites.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | integer | no | — |
| per_page | integer | no | — |
| verified_only | boolean | no | Only domains whose owner has verified them. |
| include_unlisted | boolean | no | Also return low-authority (unlisted) entries. |
| detail | string | no | Compact consumer fields by default; full adds owner profile, claims and listing metadata. |
| category | string | no | Filter by inferred topic ID from list_categories. Topics describe publisher metadata, not capabilities or correctness. |
| capability | string | no | Filter to sites explicitly publishing an MCP endpoint link. Publisher declaration alone does not prove availability. |
Look up a domain: source URLs, summary, authority, ownership verification, last check and owner-stated terms. Compact by default; detail=full adds profile, country, nested files, badge and ownership claim instructions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| detail | string | no | Compact consumer fields by default; full adds owner profile, claims and listing metadata. |
Describe optional ownership management and its four proof methods. Call begin_ownership_claim to obtain a fresh expiring proof and a private claim secret. No ownership claim is needed for discovery.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
Validate a site's llms.txt: reachability, HTML-instead-of-text, redirects to other domains, H1 title, summary, sections, links, link health, llms-full.txt and charset. Returns each check with what to fix and the file preview. Ownership management is optional and does not affect validation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
Draft an llms.txt for a site from its own homepage, sitemap and page titles. Takes 10-30 seconds. The owner reviews it and publishes it at /llms.txt. Ownership management is optional and uses a separate fresh challenge.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
Submit a domain that publishes an llms.txt so it gets crawled and indexed. Returns the verification instructions so you can continue without another call. Verified owners get: Manage your listing in the browser; ownership confirmation is optional for discovery; Breakage alerts by webhook, or email when configured, when the llms.txt stops validating; Your terms for agents (automated access, rate li
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
Start optional ownership management or recovery for a domain you control. Returns an expiring fresh public proof token and a private claim_secret shown once. Keep the secret private; publish only the verification snippet, then call verify_domain with claim_id and claim_secret. Existing keys remain valid until fresh proof succeeds. No backlink is required: DNS, meta tag and well-known file methods
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
Complete the fresh challenge from begin_ownership_claim using its private claim credentials. Checks the published proof and consumes the challenge once, returning the owner API key shown once. Public or legacy proof tokens alone cannot issue keys. Recovery replaces previous credentials and sessions. Rate limited: 10 attempts per domain per hour.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| claim_id | string | yes | — |
| claim_secret | string | yes | — |
Owner only. Replace the API key and invalidate all existing browser owner sessions. Keep the new key; it is shown once. Does not require changing the existing ownership proof.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| api_key | string | yes | The owner API key issued by verify_domain (awm_key_...). |
Owner only. Edit the listing profile (description, tags, nested llms.txt paths, contact), the terms for agents (agent_terms: automated_access = one of welcome | limited | ask | not_allowed: may agents use the site automatically?; rate_limit = short text, e.g. "60 requests/minute"; attribution = one of required | appreciated | none; attribution_text = how to credit the site (≤200 chars); pricing =
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| api_key | string | yes | The owner API key issued by verify_domain (awm_key_...). |
| description | string/null | no | — |
| tags | array | no | Lowercase slugs, e.g. ["developer-tools", "docs"]. |
| nested_llms_txt | array | no | Same-site paths of additional llms.txt files, e.g. ["/docs/llms.txt"]. |
| contact | string/null | no | — |
| agent_terms | object/null | no | Terms for automated use, shown to every agent that looks the site up. |
| webhook_url | string/null | no | Public https URL to POST breakage events to. |
| notify_email | string/null | no | — |
Owner only. Lookup count (how often agents and visitors looked the domain up), score breakdown, recent notifications, the badge embed, and the last 30 score snapshots.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| api_key | string | yes | The owner API key issued by verify_domain (awm_key_...). |
Owner only. Re-validate and update the directory listing now (once per 10 minutes). This crawl can change listing and ownership verification state and deliver configured change notifications.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| api_key | string | yes | The owner API key issued by verify_domain (awm_key_...). |
Owner only. Send a test event to the configured webhook and/or email to confirm the wiring (once per 10 minutes).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | A domain name such as example.com (no scheme, no path). |
| api_key | string | yes | The owner API key issued by verify_domain (awm_key_...). |
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 Agentwebmap 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 0.8.2 · scanned 20 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 · 3 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestf27cfeee76df8c97484c0df7695959ed79dc569105fb15e6833a7911f017b617
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 |
|---|---|---|
| resolve | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| watch_domain | external-sink | external-sink: keyword "webhook", parameter "webhook", declares readOnlyHint: false, openWorldHint: true |
| unwatch_domain | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| test_watch | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, openWorldHint: true |
| directory_stats | no tags | |
| list_categories | no tags | |
| search_llms_registry | no tags | |
| list_domains | no tags | |
| lookup_domain | no tags | |
| verification_instructions | no tags | |
| check_llms_txt | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| generate_llms_txt | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| register_domain | untrusted-inputexternal-sink | untrusted-input: keyword "crawl"; external-sink: declares readOnlyHint: false, openWorldHint: true |
| begin_ownership_claim | state-write | state-write: declares readOnlyHint: false |
| verify_domain | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| rotate_owner_key | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| update_site | external-sink | external-sink: parameter "webhook", declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| site_stats | no tags | |
| recrawl_site | untrusted-inputexternal-sink | untrusted-input: keyword "crawl"; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| test_notification | external-sink | external-sink: keyword "webhook", 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 digestf27cfeee76df8c97
Scanned2026-10-20
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 0.8.2.
0.8.2
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 Agentwebmap 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.