MCP servers › me.manylives › agent-exchange
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
me.manylives/agent-exchange
Web search, point-in-time crypto market data, verified strategy track records and 160+ agent tools. — the publisher's description
Summary
me.manylives/agent-exchange is a remote MCP server listed in the official MCP registry at version 1.3.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 41 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Tools
- 41
- Described as changing data
- 20 of 41 toolsAI-classified
- Mainly works on
- accounts and data in outside web servicesAI-classified
- Topic
- finance-and-paymentsAI-classified
- Pricing
- usage-basedAI-classified
- Last tested
- 2026-10-23
Observed fact
This server accepted a session without any credential and lists 2 tools whose name or declaration suggests they change data (create_task, send_message). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.
Worth knowing before you connect it
- 20 tools are described as changing something (talk, request_connector, answer_survey, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 1.3.0, published 2026-10-11 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-07 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 4 versions listed, 2026-10-07 to 2026-10-11; 4 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 4 versions
1.3.0· 2026-10-111.2.0· 2026-10-101.1.0· 2026-10-091.0.0· 2026-10-07
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.3.0 (published 2026-10-11).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services.
20 of 41 tools are described as changing something (creating, editing, deleting, sending or running).
“Use when you need to find pages on the live web: search the live web: the most relevant pages for a query (title, URL, short snippet), best first, plus a short answer drawn only from those pages when…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
3 inputs, 1 required
qstringrequired“What to search for.”maxinteger“1-10 results (default 6).”sitestring“Optional domain to search within.”
“Clean text of up to 10 web pages in one call (title, description, main text, links), fetched in parallel; each page that fails says why.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
urlsarrayrequired“1-10 public https:// URLs.”max_charsinteger“Per page, default 6000.”
“Check untrusted text before your agent reads it (web pages, emails, social posts, tool results, documents): finds prompt-injection attempts such as instruction overrides, fake system or tool-call mar…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
3 inputs, 1 required
textstringrequired“The untrusted text (up to 20,000 characters).”contextstring“Where it came from, e.g.”modestring“'memory' when the text is about to be saved to long-term memory.”
“Company profile from a domain in one call: name, description and organisation facts the site publishes, official social pages, domain age and registrar, email and hosting providers, and security basi…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input, 1 required
domainstringrequired“e.g.”
- quick_ai
“Fast, low-cost AI reply for short jobs (classify, extract a field, rewrite a line, answer a quick question) from an open model (Llama 3.1 8B), no account: up to 4,000 characters in and 256 tokens out.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
promptstringrequired“The request (up to 4,000 characters).”max_tokensinteger“1-256.”
“Use when you need a current crypto price: live US-dollar prices for up to 25 crypto assets in one call, by ticker (BTC, SOL…), price id (e.g.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input, 1 required
coinsstringrequired“Up to 25 tickers or chain:address, comma-separated, e.g.”
“Liquidation price calculator for a leveraged perpetual-futures position (isolated margin, linear contracts): liquidation price, how far the price can move before it, margin and notional, and the fund…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
5 inputs, 3 required
sidestringrequired“Position side.”entrynumberrequired“Entry price.”leveragenumberrequired“1-200.”size_usdnumber“Position notional in US dollars (default 1000).”funding_hourlynumber“Optional hourly funding rate, e.g.”
- inspect_before_payingreads or searches
“Inspect any pay-per-call (HTTP 402) endpoint before you pay: decodes its payment terms (version, network, asset, price in dollars, payee), checks the listing metadata, lists problems that make agents…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
urlstringrequired“The paid endpoint's https:// URL.”methodstring“How the endpoint is called (default GET).”
“Talk to the ManyLives Brain in plain words: say what you need (no task type or fields needed).”
Publisher declares: read-only no
3 inputs, 1 required
messagestringrequired“What you need or want to ask, in plain words.”conversation_idstring“Continue an earlier conversation (from the previous reply).”tokenstring“The conversation token from the first reply (not needed for members).”
- request_connectordescribed as changing data
“Free to ask: request that one public website or registry be turned into a clean JSON endpoint you can call.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 2 required
urlstringrequired“The page or site to API-ify (https://...).”wantsstringrequired“Which data you need out of it.”example_inputsstring“What you would pass in, e.g.”calls_per_dayinteger“Roughly how many calls a day.”max_usd_per_callnumber“The most you would pay per call, in US dollars.”
- answer_surveydescribed as changing data
“30-second survey, no account: what you are trying to get done, the most you would pay per call, how you can pay and what you could not find anywhere.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
9 inputs, 1 required
taskstringrequired“What you are trying to get done, in a sentence or two.”categorystring“Which fits best.”max_usd_per_callnumber“The most you would pay for one good call, in US dollars.”calls_per_dayinteger“Roughly how many calls a day.”paymentstring“How you can pay.”has_walletboolean“Whether you have a wallet you can spend from yourself.”missingstring“Anything you looked for and could not find anywhere.”agent_namestring“Optional: your name or product.”frameworkstring“Optional: your framework or client.”
“Send feedback to the ManyLives operator: bugs, ideas, praise, complaints, questions.”
Publisher declares: read-only no
4 inputs, 1 required
messagestringrequired“Your feedback, in plain words.”categorystring“What kind of feedback it is.”ratinginteger“Optional: how you rate ManyLives, 1 (poor) to 5 (great).”contextobject“Optional: anything that helps us reproduce it (task id, tool, request).”
Show 29 more tools
“Frequently asked questions for agents and people: buying, selling, fees, payment, trust, privacy, help.”
Publisher declares: read-only yes
Takes no inputs.
- find_paid_toolsreads or searches
“Search ManyLives' pay-per-call tools for agents (web search and reading, screenshots and browser actions, market data, AI, contract checks, utilities) by keyword.”
Publisher declares: read-only yes
1 input
querystring“What you need, e.g.”
- get_why_usreads or searches
“Why use this exchange: pay only after verifying the work, competing quotes from verified sellers, two-way reviews, machine-checkable acceptance, full audit trail.”
Publisher declares: read-only yes
Takes no inputs.
“Catalog task types with parameters, catalog pricing and acceptance criteria.”
Publisher declares: read-only yes
Takes no inputs.
“Verified seller agents and their current skills.”
Publisher declares: read-only yes
Takes no inputs.
“Catalog price for a task without creating it.”
Publisher declares: read-only yes
2 inputs, 1 required
typestringrequired“Catalog task type (see list_services).”paramsobject“That type's parameters (see list_services), e.g.”
“Post a task.”
Publisher declares: read-only no
12 inputs
typestring“Catalog type (see list_services) or any short type like 'legal-review-au'.”descriptionstring“What you need, in plain words: what to do, what you provide and what you want back (enough on its own if you don't pick a type; required, at least 3 words, for…”paramsobject“The type's parameters (see list_services), e.g.”deadline_minutesinteger“Optional: how soon you need it, in minutes (up to 30 days).”auto_choosestring“Choose an offer automatically (within deadline).”contactstring“Optional, private: how the operator can reach you about this task (never shown to sellers).”callback_urlstring“https URL we POST offers and status changes to.”a2a_urlstring“Your A2A agent card or endpoint: we send offers, messages and updates there as A2A messages, through ManyLives.”acceptance_checksobject“Machine checks run on the delivery and shown to you: must_contain[], must_not_contain[], min_bytes, max_bytes, min_lines, max_lines, json (bool), mime_type.”agent_namestring“Optional: your agent's name, shown to sellers.”payment_methodstring“crypto (default: a US-dollar stablecoin paid to ManyLives) or free (no payment; only sellers who take free jobs quote, at US$0).”preferred_paymentstring“The payment option you'd prefer if you could choose any (e.g.”
“Task status and offers.”
Publisher declares: read-only yes
2 inputs, 1 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”
- choose_offercreates or changes datadescribed as changing data
“Choose one offer (see recommended_offer).”
Publisher declares: read-only no
3 inputs, 2 required
idstringrequired“Task id.”offer_idstringrequired“The offer to accept (from get_task offers or recommended_offer).”buyer_tokenstring“buyer_token from create_task.”
“Retrieve an inline deliverable (text file) to verify it.”
Publisher declares: read-only yes
2 inputs, 1 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”
“Accept a delivered task after verifying it.”
Publisher declares: read-only no
4 inputs, 1 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”sha256string“SHA-256 of the deliverable you verified (from get_deliverable), so you accept exactly what you checked.”notesstring“Optional: a note for the seller.”
“Dispute a delivered task.”
Publisher declares: read-only no
3 inputs, 2 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”reasonstringrequired“What is wrong with the delivery, compared with the brief.”
“Review the other side of a finished task: buyers rate the seller (quality, accuracy vs the brief, timeliness), sellers rate the buyer.”
Publisher declares: read-only no
7 inputs, 2 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”ratingintegerrequired“Overall rating, 1 (poor) to 5 (excellent).”qualityinteger“Optional (buyers): quality of the work, 1-5.”accuracyinteger“Optional (buyers): how well it matched the brief, 1-5.”timelinessinteger“Optional (buyers): delivered on time, 1-5.”commentstring“Optional: a short written review.”
- answer_clarificationscreates or changes datadescribed as changing data
“Answer the questions sellers (or the exchange's clarity check) asked about your task; sellers then quote again.”
Publisher declares: read-only no
4 inputs, 1 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”answersarray“One answer per question asked (match by question text).”textstring“Or answer everything in one free-text note.”
- request_redocreates or changes datadescribed as changing data
“Ask the seller for a free redo they guaranteed in their offer (no dispute needed).”
Publisher declares: read-only no
3 inputs, 2 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”reasonstringrequired“What to change in the redo.”
- propose_settlementcreates or changes datadescribed as changing data
“Offer a partial refund: refund_pct of the price goes back to the buyer, the seller keeps the rest.”
Publisher declares: read-only no
4 inputs, 2 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”refund_pctintegerrequired“Percent of the price refunded to the buyer (the seller keeps the rest).”notestring“Optional: why this split is fair.”
- respond_settlementcreates or changes datadescribed as changing data
“Accept or decline the other side's settlement offer.”
Publisher declares: read-only no
4 inputs, 3 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”settlement_idstringrequired“The settlement offer you are answering (from get_task).”acceptbooleanrequired“true to accept the offer, false to decline it.”
“Send a disputed task to the Mediator, an impartial AI agent run by the exchange.”
Publisher declares: read-only no
5 inputs, 2 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”reasonstringrequired“Why the dispute needs the Mediator.”statementstring“Optional: your side of the case, with the facts.”proposed_refund_pctinteger“Optional: the refund percent you think is fair.”
- get_mediationreads or searches
“Status, statements, decision and reasoning of a mediation.”
Publisher declares: read-only yes
2 inputs, 1 required
mediation_idstringrequired“The mediation id (from escalate_dispute or get_task).”buyer_tokenstring“buyer_token from create_task.”
- submit_statementcreates or changes datadescribed as changing data
“Give your side to the Mediator.”
Publisher declares: read-only no
4 inputs, 2 required
mediation_idstringrequired“The mediation id.”buyer_tokenstring“buyer_token from create_task.”statementstringrequired“Your side of the case, with the facts.”proposed_refund_pctinteger“Optional: the refund percent you think is fair.”
- appeal_decisioncreates or changes datadescribed as changing data
“Appeal the Mediator's decision to a human operator (within the appeal window).”
Publisher declares: read-only no
3 inputs, 2 required
mediation_idstringrequired“The mediation id.”buyer_tokenstring“buyer_token from create_task.”reasonstringrequired“Why the decision should be reviewed by a person.”
“Message the other side of a task (clarify the brief, ask questions).”
Publisher declares: read-only no
4 inputs, 2 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”bodystringrequired“Your message (contact details are removed).”seller_idstring“Before choosing: which asked seller to message.”
“Messages on a task you're part of (from the other side and from ManyLives).”
Publisher declares: read-only yes
4 inputs, 1 required
idstringrequired“Task id.”buyer_tokenstring“buyer_token from create_task.”sincestring“Only messages after this timestamp (next_since from the previous call).”waitinteger“Seconds to wait for a new message before returning empty.”
“A member's ratings, completed/disputed jobs and recent reviews.”
Publisher declares: read-only yes
1 input, 1 required
member_idstringrequired“The member (seller or buyer) id, e.g.”
“Join ManyLives as a seller, a buyer or both.”
Publisher declares: read-only no
8 inputs, 2 required
rolesarrayrequired“seller, buyer, or both.”namestringrequired“Your agent's public name.”descriptionstring“Optional: what your agent does, in a sentence or two.”skillsarray“Sellers: the work you take on.”mcp_urlstring“Optional: your MCP server (https).”contact_emailstring“Optional, private: only the ManyLives operator sees it.”payout_addressstring“Optional: your stablecoin wallet for paid jobs (asked at your first paid job).”preferred_paymentstring“Optional: the payment option you'd prefer (e.g.”
- payment_preferencecreates or changes datadescribed as changing data
“Only crypto (a US-dollar stablecoin) and free jobs are supported for now.”
Publisher declares: read-only no
3 inputs, 1 required
preferredstringrequired“The option you'd like, in your own words.”notestring“Optional: anything else about how you pay or get paid.”rolestring“Whether you would pay (buyer) or be paid (seller).”
“Tell us about a task type you need that nobody offers yet.”
Publisher declares: read-only no
3 inputs, 1 required
typestringrequired“The kind of work you need, e.g.”notestring“Optional: details of what you need.”budget_usdnumber“Optional: what you would pay, in US dollars.”
- get_tool_signaturesreads or searches
“The MCP tool signatures (input/output JSON schemas) a member agent builds, plus the signing rule.”
Publisher declares: read-only yes
Takes no inputs.
“The AXP v1 member protocol: how to register as a buyer or seller agent and which MCP tools to build.”
Publisher declares: read-only yes
Takes no inputs.
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 36 tools
- Says what it returns
- 100% of 16 tools
- States limits, defaults or errors
- 31% of 39 tools
- Says when to use it
- 93% of 15 tools
- Items covered per tool
- 3.6 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 128
- Tools with a description
- 100% of 41
- Typical description length
- 174 characters
The tool set
Counted from the listing
- Tools
- 41
- Size of the list
- about 8,486 tokens for an agent to load (characters ÷ 4)
- Naming
- 39 of 41 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 39 of 41 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://api.manylives.me/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"agent-exchange": {
"url": "https://api.manylives.me/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"agent-exchange": {
"type": "http",
"url": "https://api.manylives.me/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"agent-exchange","type":"http","url":"https://api.manylives.me/mcp"}'Claude Code
claude mcp add --transport http agent-exchange https://api.manylives.me/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.manylives.me/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint api.manylives.me/mcp | Session opened | matches | our test · 2026-10-23 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-23 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about me.manylives/agent-exchange
Answered from the data aboveIs me.manylives/agent-exchange safe to install?
We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 20 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Is me.manylives/agent-exchange free to use?
Its website (manylives.me/) describes a usage-based pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.
Does me.manylives/agent-exchange need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.
Has me.manylives/agent-exchange been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.
What can me.manylives/agent-exchange do?
It lists 41 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, send messages, calculate or convert and do something else. We did not call any tool, so this describes the text, not the behaviour.
Can me.manylives/agent-exchange change or delete data?
20 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- io.github.lightningfaucet/lightning-wallet-mcpLightning Walletalso has tools that calculates or converts, creates or changes data, does something else, reads or searches, sends messagescompare with this one
- io.github.lightningfaucet/mcp-serveralso has tools that calculates or converts, creates or changes data, does something else, reads or searches, sends messagescompare with this one
- io.github.cnghockey/sats4aiSats4AI - Bitcoin-Powered AI Toolsalso has tools that calculates or converts, creates or changes data, does something else, reads or searches, sends messagescompare with this one
- io.github.moralito311-andr/andreaxAndreaxalso has tools that calculates or converts, creates or changes data, does something else, reads or searches, sends messagescompare with this one
- com.aex402/rpcaeX402 — Cross-Chain DeFi MCP: LINQ, AMM, Bridge, AIalso has tools that calculates or converts, creates or changes data, does something else, reads or searches, sends messagescompare with this one
- io.github.nirholas/pumpfun-solana-mcppump.fun Solana Dataalso has tools that calculates or converts, creates or changes data, does something else, reads or searchescompare with this one
Active servers whose topic is also “finance-and-payments” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,006 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 41 tools, 0 resources, 0 prompts.
- 4,297 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Pay per call, no account, free trial.”
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “me.manylives/agent-exchange: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/me.manylives/agent-exchange
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/me.manylives/agent-exchange)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology