Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content
Nothing to run from here
Agent Paywire library 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.
96/100
tool-list score
15
tools declared
remote
at its publisher
—
calls last 7d
What it does
Library (L402, x402, Lightning, stablecoins): 18 read-only tools plus 3 writers.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agent-paywire-library-mcp https://mcp.agentpaywire.com/mcp
# 2 — ask your agent for something these tools do
# search_library, search, get_source and 12 more
Agent Paywire library 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
agentpaywire1 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 agent-paywire-library-mcp https://mcp.agentpaywire.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
15 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 third-party library sources for every word in query: each word must appear, case-insensitively and as a substring, in id, title, summary, publisher, authors or tags. Use this for multi-word or author lookups. Use search for a single phrase with exact tag, type or updated_since filters, and get_source when you already have an id. Results are newest date_published first, undated last; limit c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Space-separated words; every word must match (AND), case-insensitive substring. Example: lightning l402. An empty string matches everything. |
| category | string | no | Optional category id from list_categories, e.g. bitcoin-lightning. Combined with query (AND). |
| featured_only | boolean | no | true returns only featured sources. Omit or false to include all. |
| limit | integer | no | Maximum rows, 1-50, default 10. Values above 50 are rejected; there is no offset, so narrow the query to see other matches. |
Filter third-party library sources by one case-insensitive substring in id, title, summary or publisher, plus exact category, tag, type, featured or updated_since. All given filters must match. updated_since is exclusive (verified_at later than the date). A value that is not a real YYYY-MM-DD date returns an isError result. Use search_library for multi-word queries or matches in authors and tags,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | no | One substring, matched case-insensitively against id, title, summary or publisher (not authors or tags). Example: L402. Spaces are part of the substring. |
| category | string | no | Category id from list_categories, e.g. bitcoin-lightning. |
| tag | string | no | One tag, exact match, e.g. l402. |
| type | string | no | Source type from the enum, e.g. spec. |
| featured | boolean | no | true returns only featured sources. Omit to include all. |
| updated_since | string | no | YYYY-MM-DD calendar date; returns sources whose verified_at is later than this date (exclusive). A value that is not that form returns an isError result. Example: 2026-10-01. |
| limit | integer | no | Maximum rows, 1-50, default 10. Values above 50 are rejected; there is no offset. |
Fetch one third-party library source card by id: title, publisher, authors, date_published, url, type, category, summary, tags, verified_at and featured. Ids are the sources[].id values from search, search_library or latest_sources, or changes_since entries of kind library (no prefix). Use search or search_library when you have no id, and get_article for Agent Paywire's own articles. An unknown id
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Source id exactly as returned in sources[].id, e.g. lightning-labs-l402-for-agents. Case and hyphens must match. |
List the eight library categories with id, label, featured flag, source count and links to each category's JSON, Markdown and HTML pages; Bitcoin and Lightning is first. Use it to get a valid category id before filtering search, search_library or latest_sources, or to see how many sources each topic holds. It does not list the sources themselves: use latest_sources with category for that. Free, no
No parameter schema on file.
Return the newest third-party library sources, sorted by date_published descending, with undated sources last. category keeps one category (ids from list_categories) before limit is applied; limit caps rows at 1-50 (default 10). There is no offset or cursor, and count is the rows returned, not the library total. Use changes_since to sync everything changed after a date, including articles, dataset
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Maximum rows to return, 1-50, default 10. Values above 50 are rejected, and there is no offset to page further. |
| category | string | no | Optional category id from list_categories, e.g. bitcoin-lightning. Filters before the limit is applied; omit for all categories. |
List all of Agent Paywire's own published articles with slug, title, summary, date, status, tags and URLs, in one unpaged response. Use get_article with a slug to read the full Markdown. For third-party papers, specs and reports, use search_library or latest_sources: articles are not library sources and do not appear there. Free, no auth.
No parameter schema on file.
Return one Agent Paywire article as Markdown with YAML front matter, by slug. Get slugs from list_articles, or from changes_since after removing the article: prefix. Use get_source instead for third-party library sources, which are not articles. An unknown slug returns an isError result (No article with slug ...). Free, no auth.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Article slug exactly as in list_articles articles[].slug, e.g. machine-native-economy. Do not include the article: prefix that changes_since uses. |
List every record whose verified_at is later than cursor (exclusive) across library sources, articles, datasets, bots and support notes, with kind, id, title, url and verified_at. There is no limit or paging, so an old cursor can return the whole catalog (over 100 entries, about 43 KB); store the latest verified_at you saw and pass it next time. Non-library ids are prefixed (article:, dataset:, bo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cursor | string | yes | Date as YYYY-MM-DD, e.g. 2026-10-19. Records with verified_at strictly later are returned; today's date usually returns 0 rows. Other formats are rejected. |
Return source-cited facts for agent payment protocols: spec URL, HTTP status codes and headers, payment rail, networks, facilitators, client libraries, pay flow and an example. Every fact carries its source URL and verified_at; null means the cited page does not state it. Omit id for all nine protocols in a protocols array (about 23 KB); pass id for that one protocol's object only. Use this for ho
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Lowercase protocol id from the enum, e.g. l402. Set it to get one protocol object (smaller response); omit it to get every protocol in a protocols array. |
Return the voluntary support descriptor: donation methods (Bitcoin on-chain, Lightning BOLT12, USDC on EVM networks and Solana) with addresses, suggested sat amounts, and the paid_api block (L402 over Lightning, 100 sats for 100 credits, valid 30 days). Calling it never sends money or creates an invoice, and the data stays free whether or not anyone pays. Use it when a user wants to tip or asks ho
No parameter schema on file.
Return the agent trust checklist for agentpaywire.com: commitments on stable URLs, errors and limits, and naming, each with status met or partial and evidence URLs, plus the paid API's error codes, rate-limit policy, credit terms and the list of MCP tools. Use it to judge whether the site and its paid API are dependable or to look up an error code; use get_support_info for donation addresses and p
No parameter schema on file.
List every training and evaluation dataset card in the catalog (payments, Lightning, fraud, agent tool use) in one unpaged response; Agent Paywire's own library dataset is first. Each entry has id, name and url; count is the number of cards. Cards are metadata: nothing is downloaded. Use get_dataset with an entry id for access terms and mirror rights; use search_library with category datasets-benc
No parameter schema on file.
Return one training or eval dataset card by id: name, publisher, url, access (open, login, or terms-acceptance), mirror_allowed and notes. A card is metadata only; this does not download dataset files, so follow url for the data. Take the id from list_datasets entries, or from changes_since after removing the dataset: prefix. An unknown id returns an isError result (the card file is 404). Use list
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Dataset id exactly as in list_datasets entries[].id, e.g. agentpaywire-library. Do not include the dataset: prefix that changes_since uses. |
List every verified public agent or bot that pays, gets paid, or connects a wallet, with maker, protocols, license status, url, verified_at and funds_or_keys (true when the software can access a wallet or keys). Inclusion needs a public repo or demo, a known maker, and a push in the 12 months before verification. Use this to find or vet such software; use search_library for papers and docs about a
No parameter schema on file.
Return one verified public agent or bot by id: name, maker, description, protocols, url, license, license_verified, license_url, verified_at, http_status, archive_url, funds_or_keys and notes. funds_or_keys is true when the software can access a wallet or keys. Take the id from list_bots entries[].id, or from changes_since after removing the bot: prefix. An unknown id returns an isError result (No
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Bot id exactly as in list_bots entries[].id, e.g. lnget. Do not include the bot: prefix that changes_since uses. |
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 Agent Paywire library 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 96 / 100
Release 1.1.0 · scanned 28 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 score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest204edaceb4312423c1ebd80924d996184021752c4343d54b03fa032cc50ded35
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_library | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_source | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| list_categories | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| latest_sources | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_articles | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_article | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| changes_since | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| protocol_facts | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_support_info | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_trust_checklist | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_datasets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_dataset | untrusted-input | untrusted-input: keyword "browse", declares openWorldHint: true (interacts with entities outside the server) |
| list_bots | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_bot | untrusted-input | untrusted-input: keyword "browse" |
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest204edaceb4312423
Scanned2026-10-28
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 1.1.0.
1.1.0
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 Agent Paywire library 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.