MCP servers › io.github.w3tech › agent-rpc-mcp

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

io.github.w3tech/agent-rpc-mcp

Read chain data on 200+ networks and Sui: transactions, logs, balances, objects, ABI-decoded. — the publisher's description

7 of 9 record checks metRead-only · tools listed 2026-10-23Topic: finance-and-payments · AI-classifiedversion 0.2.7DockerfileMITstandard input/output, streamable HTTP25 tools

Summary

io.github.w3tech/agent-rpc-mcp is a remote and local MCP server listed in the official MCP registry at version 0.2.7. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 25 tools, 0 resources and 0 prompts.

Record checks

7 of 9 record checks met

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
not met: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not met: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

#6,037 of 15,112 packages by monthly downloads, tied with 11 others
Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote and local package
Transport: standard input/output, streamable HTTP
Sign-in: none needed to open a session
Package: npm · listed version current
License: MIT
Dependencies: no known high or critical advisories
Repository: public
Tools: 25
Described as changing data: 0 of 25 toolsAI-classified
Mainly works on: nothing outside itself: it only answers questionsAI-classified
Topic: finance-and-paymentsAI-classified
Last tested: 2026-10-23

Add to your client

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

0.2.7, published 2026-10-22 (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 2026-10-22; 4 in the 90 days before the 2026-10-23 snapshot.

Most recent 4 versions

0.2.7 · 2026-10-22
0.2.5 · 2026-10-12
0.2.5-0 · 2026-10-12
0.2.4 · 2026-10-07

(versions still listed in the registry only)

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 0.2.7 (published 2026-10-22).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

25tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: nothing outside itself: it only answers questions.

None of its 25 tools are described as changing anything.

getAccountBalanceon 1 other serverreads or searches
“Balance of an account across many blockchains, by 0x address or ENS name, via the Ankr Advanced API indexer.”
Publisher declares: read-only yes · open-world yes
4 inputs, 1 required
- addressstringrequired“Wallet address (0x...) or ENS name (*.eth)”
- blockchainsarray“Chains to query; omit to query every chain”
- maxTokensinteger“Max assets to list, sorted by USD value descending (default 20, max 100).”
- minUsdnumber“Only list assets worth at least this many USD; the rest are summarised as dust.”
getTokenPriceon 1 other serverreads or searches
“USD price of a token on one blockchain: pass a contract address for an ERC-20, or leave it empty for the native coin.”
Publisher declares: read-only yes · open-world yes
3 inputs
- chainstring“Chain slug, e.g.”
- blockchainstring“DEPRECATED alias for `chain`.”
- contractAddressstring“Contract address of the token.”
getTransactionon 1 other serverreads or searches
“Get a transaction by its hash on one blockchain, with tier-2 decoding requested.”
Publisher declares: read-only yes · open-world yes
3 inputs, 2 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- txHashstringrequired“Transaction hash (0x + 64 hex) or Sui digest”
- includestring“Which parts to fetch.”
getLogsreads or searches
“Event logs on one chain, filtered by address and/or topics over a block range.”
Publisher declares: read-only yes · open-world yes
8 inputs, 1 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- addressstring“Emitting contract; Sui: package[::module]”
- topicsarray“Topic filters (0x + 64 hex, or null to wildcard); topics[0] is the event signature hash.”
- eventTypestring“Sui: Move event type 0xpkg::module::Name”
- senderstring“Sui: the emitting transaction's sender, 0x + 64 hex”
- fromBlockinteger or string“From block: decimal, 0x-hex, or tag (default latest)”
- toBlockinteger or string“To block: decimal, 0x-hex, or tag (default latest)”
- maxLogsinteger“Max logs to DISPLAY (default 50, max 1000).”
getBlockreads or searches
“Get a block by a 0x-64 hash, a block number (decimal or 0x-hex), or a tag (latest, finalized, safe, earliest, pending).”
Publisher declares: read-only yes · open-world yes
3 inputs, 2 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- blockinteger or stringrequired“Block number (decimal or 0x-hex), a 0x-64 block hash, or a tag.”
- includeTxsboolean“Include full (decoded) transactions instead of just hashes (default false)”
getBalancesreads or searches
“An address's balances on ONE chain: native via eth_getBalance plus, by default, ERC-20 balances with USD from the Ankr Advanced API indexer (tier 0).”
Publisher declares: read-only yes · open-world yes
5 inputs, 2 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- addressstringrequired“Address (0x...) or ENS name”
- includeTokensboolean“Include ERC-20 token balances via AAPI (default true)”
- maxTokensinteger“Max entries in `tokens` (default 20, max 100).”
- minUsdnumber“Only list tokens worth at least this many USD; everything below is bucketed into `dust`.”
getWalletActivityreads or searches
“An address's recent transactions on one blockchain, newest first, via the Ankr Advanced API indexer.”
Publisher declares: read-only yes · open-world yes
3 inputs, 2 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- addressstringrequired“Wallet address (0x...) or ENS name”
- pageSizeinteger“Items per page (default 25, max 100)”
resolveContractreads or searches
“Inspect an address on a chain: whether it is a contract, best-effort ERC-20 token metadata (name, symbol, decimals), and EIP-1967 proxy detection (implementation address).”
Publisher declares: read-only yes · open-world yes
2 inputs, 2 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- addressstringrequired“Contract or account address”
searchChainreads or searches
“Resolve an on-chain IDENTIFIER to the object it names.”
Publisher declares: read-only yes · open-world yes
2 inputs, 1 required
- querystringrequired“0x tx/block hash, 0x address, or block number.”
- chainstring“Chain (default eth)”
expandResultreads or searches
“Continue a paged result using the opaque cursor returned by a previous tool call.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
- cursorstringrequired“The opaque cursor string from a previous tool result”
rpcCallreads or searches
“Call ANY JSON-RPC method on a supported chain: the escape hatch beyond the routed tools (eth_call, eth_estimateGas, eth_getCode, debug_trace*, trace_*).”
Publisher declares: read-only yes · open-world yes
4 inputs, 2 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- methodstringrequired“JSON-RPC method, e.g.”
- paramsarray“Positional JSON-RPC params (default [])”
- tiernumber“Requested TORPC tier (default 2)”
suiGetObjectsreads or searches
“Move objects by id, in ONE batch call: each answer carries the object's id, type, version, owner and its decoded Move fields under json.”
Publisher declares: read-only yes · open-world yes
2 inputs, 1 required
- idsarrayrequired“Object ids to read, 50 at most.”
- versionstring“Read this past version instead of the live object.”

Show 13 more tools

suiListOwnedObjectsreads or searches
“Every object an address owns, page by page, out of the node's own owner index.”
Publisher declares: read-only yes · open-world yes
3 inputs, 1 required
- ownerstringrequired“The owning address.”
- typestring“Move type filter, with or without its type parameters.”
- pageSizeinteger“How many objects to return (default 50, max 200).”
suiListDynamicFieldsreads or searches
“Whatever a Move package stored under one object's UID: tables, bags and dynamic object fields, listed from the parent id.”
Publisher declares: read-only yes · open-world yes
2 inputs, 1 required
- parentstringrequired“The id of the object whose dynamic fields are listed.”
- pageSizeinteger“How many fields to return (default 50, max 200).”
suiGetPackagereads or searches
“What a published Move package declares, so a caller can pick what to inspect next.”
Publisher declares: read-only yes · open-world yes
3 inputs, 1 required
- packagestringrequired“Package id (0x2 is the framework)”
- modulestring“One module to return in full”
- maxModulesinteger“Rows the index lists before it truncates (default 50).”
suiGetFunctionreads or searches
“One Move function's signature: visibility, whether it is an entry function, its type parameters, its parameter types and its return types — what a programmable transaction block needs in order to cal…”
Publisher declares: read-only yes · open-world yes
3 inputs, 3 required
- packagestringrequired“Package id (0x2 is the framework)”
- modulestringrequired“Module name”
- functionstringrequired“Function name”
suiResolveNamereads or searches
“Resolve a SuiNS name (something.sui) to the address it points at, or an address back to its name.”
Publisher declares: read-only yes · open-world yes
2 inputs
- namestring“Forward: a .sui name”
- addressstring“Reverse: a Sui address”
suiSimulateTransactionreads or searches
“Run a transaction against current state and report what it WOULD do, without submitting it: whether it succeeds or which Move abort stops it and in which command, the gas it consumes, the objects it …”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
- transactionBytesstringrequired“The transaction to simulate: a base64 BCS TransactionData.”
suiWatchEventsreads or searches
“Follow Move events from now on, by POLLING — nothing is pushed.”
Publisher declares: read-only yes · open-world yes
4 inputs
- addressstring“Emitting Move code: package, or package::module”
- eventTypestring“Move event type 0xpkg::module::Name”
- senderstring“The emitting transaction's sender, 0x + 64 hex”
- maxLogsinteger“Max events to DISPLAY per poll (default 50, max 1000).”
getNFTsreads or searches
“NFTs one wallet holds on one chain: collection, name, token id, contract, standard (ERC721/1155), image URL.”
Publisher declares: read-only yes · open-world yes
4 inputs, 2 required
- chainstringrequired“Chain, from listChains aapiChains”
- addressstringrequired“Owner wallet address (0x...) or ENS name”
- pageSizeinteger“Items per page (default 20, max 50)”
- pageTokenstring“nextPageToken from the previous page”
getTokenHolderson 1 other serverreads or searches
“Who holds an ERC-20 token on one chain, largest balance first, plus the total holder count.”
Publisher declares: read-only yes · open-world yes
4 inputs, 2 required
- chainstringrequired“Chain, from listChains aapiChains”
- contractAddressstringrequired“ERC-20 token contract address”
- pageSizeinteger“Holders per page (default 20)”
- pageTokenstring“nextPageToken from the previous page”
getTokenPriceHistoryreads or searches
“Historical USD price series for a token contract on a chain, via the Ankr Advanced API indexer: a list of { timestamp, usd, block } quotes.”
Publisher declares: read-only yes · open-world yes
6 inputs, 2 required
- chainstringrequired“Chain, from listChains aapiChains”
- contractAddressstringrequired“ERC-20 token contract address”
- fromTimestampinteger“Start UNIX timestamp (seconds)”
- toTimestampinteger“End UNIX timestamp (seconds)”
- intervalinteger“Interval between quotes, in seconds”
- limitinteger“Max quotes (default 100)”
getInteractionsreads or searches
“List the blockchains an address has interacted with, via the Ankr Advanced API indexer.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
- addressstringrequired“Address (0x...) or ENS name”
listChainsreads or searches
“Discover chain support.”
Publisher declares: read-only yes · open-world no
Takes no inputs.
describeMethodsreads or searches
“What a JSON-RPC method takes, and whether this key can actually call it on this chain.”
Publisher declares: read-only yes · open-world yes
3 inputs, 1 required
- chainstringrequired“Chain slug as in rpc.ankr.com/<chain> — any chain Ankr serves (see listChains)”
- methodsarray“Methods to describe (max 12); omit for the whole catalogue”
- probeboolean“Ask the node whether each method is served (needs methods)”

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 25 tools
Says what it returns: 100% of 25 tools
States limits, defaults or errors: 96% of 25 tools
Says when to use it: 100% of 25 tools
Items covered per tool: 4.0 of 4 on average

Counted from the listing

Parameters with a description: 100% of 76
Tools with a description: 100% of 25
Typical description length: 649 characters

The tool set

Counted from the listing

Tools: 25
Size of the list: about 9,127 tokens for an agent to load (characters ÷ 4)
Naming: 25 of 25 names use camelCase

AI reading: easy to mix up

No pair found.

The AI items cover 25 of 25 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. 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 npm package @w3tech.io/agent-rpc-mcp

This entry needs values of your own (marked < > or { } in the config below), so there is no one-click link: paste the config and fill them in.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "agent-rpc-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@w3tech.io/agent-rpc-mcp@0.2.7"
      ],
      "env": {
        "ANKR_API_KEY": "<ANKR_API_KEY>"
      }
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-rpc-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@w3tech.io/agent-rpc-mcp@0.2.7"
      ],
      "env": {
        "ANKR_API_KEY": "<ANKR_API_KEY>"
      }
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "agent-rpc-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@w3tech.io/agent-rpc-mcp@0.2.7"
      ],
      "env": {
        "ANKR_API_KEY": "${input:ankr-api-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "ankr-api-key",
      "description": "ANKR_API_KEY",
      "password": true
    }
  ]
}

Claude Code

claude mcp add --env "ANKR_API_KEY=<ANKR_API_KEY>" --transport stdio agent-rpc-mcp -- npx -y @w3tech.io/agent-rpc-mcp@0.2.7

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -e "ANKR_API_KEY=<ANKR_API_KEY>" -- npx -y @w3tech.io/agent-rpc-mcp@0.2.7

Replace <ANKR_API_KEY> with your own values; the entry marks ANKR_API_KEY as secret, so keep the file out of version control.
This runs the publisher's code on your machine (npx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

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://mcp.ankr.com/rpc

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-rpc-mcp": {
      "url": "https://mcp.ankr.com/rpc"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "agent-rpc-mcp": {
      "type": "http",
      "url": "https://mcp.ankr.com/rpc"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"agent-rpc-mcp","type":"http","url":"https://mcp.ankr.com/rpc"}'

Claude Code

claude mcp add --transport http agent-rpc-mcp https://mcp.ankr.com/rpc

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://mcp.ankr.com/rpc --transport http

Optional settings the entry also lists (left out above): Authorization.
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.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 0.2.7
Latest stable: 0.2.7
Status: current
Withdrawn: no

Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-iXc5tTkHMzHRP5hgA…
Signature: signed
License: MIT

Source: the package registry · 2026-10-23.

Usage

Downloads: 439 in the last month

Source: api.npmjs.org · 2026-10-23.

Does the registry listing match what we found?

Feature #6

The 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 mcp.ankr.com/rpc	Session opened	matches	our test · 2026-10-23
A secret is declared as required	Opened a session without any credential	differs	our test · 2026-10-23
Version 0.2.7 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/w3tech/agent-rpc-mcp-public	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.w3tech · 2 servers
GitHub owner: an organization (w3tech)
Build record: signed

Repository: github.com/w3tech/agent-rpc-mcp-public
Stars: 0
Repository age: 31–90 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

7 of 9 record checks met

#6,037 of 15,112 packages by monthly downloads, tied with 11 others
Not ranked by stars: 0 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
MetPackage names its licence with a standard (SPDX) identifierMIT
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

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 io.github.w3tech/agent-rpc-mcp

Answered from the data above

Is io.github.w3tech/agent-rpc-mcp safe to install?

We do not rate servers as safe or unsafe. 7 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does io.github.w3tech/agent-rpc-mcp need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares a required secret.

Has io.github.w3tech/agent-rpc-mcp been security tested?

Partly. 3 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.

What can io.github.w3tech/agent-rpc-mcp do?

It lists 25 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. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.w3tech/agent-rpc-mcp change or delete data?

None of its 25 tools is described as changing anything (our AI model's reading of the descriptions; nobody checked it by hand). We did not call any tool.

Does io.github.w3tech/agent-rpc-mcp publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 0.2.7, the latest stable release on npm.

Where is the source code of io.github.w3tech/agent-rpc-mcp?

In github.com/w3tech/agent-rpc-mcp-public, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A 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.vybenetwork/solana-mcp-vybeSolana MCP by Vybealso has tools that reads or searchescompare with this one
io.github.mnemox-ai/tradememory-protocolalso has tools that reads or searchescompare with this one
io.github.agent-next/polymarket-paper-traderPolymarket Paper Traderalso has tools that reads or searchescompare with this one
io.github.openaccountants/openaccountantsOpenAccountantsalso has tools that reads or searchescompare with this one
io.github.koreal6803/finlab-aialso has tools that reads or searchescompare with this one
io.github.xang1234/stockscreen-mcpStock Screeneralso has tools that 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

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

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: exercised

3 exercised12 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 12

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

Does not apply to this server · 3

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

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
1,721 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 25 tools, 0 resources, 0 prompts.
4,802 msFinished: 3 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.

TopicAI-classified

finance-and-payments

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

No value: the AI answer was held back because the quoted text did not clearly support it.

Programming language

Dockerfile

api.github.com · 2026-10-23

Hosting type

remote and local package

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

standard input/output, streamable HTTP

registry · 2026-10-23

Required credentials

requires a secret

registry · no declaration is not a guarantee

Package registry

npm

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-23

Integrity hash

declared (sri)

package registry · 2026-10-23

Signature / provenance

signed

package registry · 2026-10-23

Dependency advisories

none known

npm audit · 2026-10-23

Popularity

439 downloads a month

package registry · 2026-10-23

Publisher signals

owner: an organization · repository age: 31–90 days · stars: 0–9 · build record: signed

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

either (remote or your machine)

where it runs, from the hosting type

“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. “io.github.w3tech/agent-rpc-mcp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.w3tech/agent-rpc-mcp

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

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.w3tech/agent-rpc-mcp)](https://protocolprobe.com/mcp/servers/io.github.w3tech/agent-rpc-mcp)

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