Skip to content

MCP servers › finance.souvenir › coins

MCP server · registry snapshot 2026-11-14 · last tested 2026-11-19

coins MCP server

Registry name finance.souvenir/coins

Souvenir — the publisher's title

by souvenir.finance · domain (the registry's namespace rule)Website ↗

Souvenir prize coins on Solana: search coins and rounds, launch and trade coins, claim wins. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-11-19version 1.3.0streamable HTTP26 tools

Summary

finance.souvenir/coins is a remote MCP server listed in the official MCP registry at version 1.3.0, under the namespace of the domain souvenir.finance. On 2026-11-19 ProtocolProbe connected to it in read-only mode and read its inventory: 26 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  • not applicable: The version the registry lists can be installed and is not withdrawn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

Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Tools
26
Last tested
2026-11-19

Tool list size

14,400 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (25 tools). Counted with Anthropic's token counter on 2026-11-14, from the tool list we read on 2026-11-14. Median across 28,560 counted servers: 2,657 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-19 (souvenir.finance), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.3.0).

Add to your client

Observed fact

This server accepted a session without any credential and lists 6 tools whose name or declaration suggests they change data (send_transaction, claim_sol, create_coin_key, revoke_coin_key, set_coin_mode and 1 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-19.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-19
Mode
read-only (no tool calls)
Latest version
1.3.0, published 2026-11-13 (registry, as of the 2026-11-14 snapshot)
First listed version
2026-11-10 (earliest version still in the registry; older removed versions would be earlier)
Version history
3 versions listed, 2026-11-10 to 2026-11-13; 3 in the 90 days before the 2026-11-14 snapshot.
Most recent 3 versions
  • 1.3.0 · 2026-11-13
  • 1.2.0 · 2026-11-10
  • 1.0.0 · 2026-11-10
(versions still listed in the registry only)
Registry data
snapshot 2026-11-14
Package and repository
checked 2026-11-14
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

Version 1.2.0 (published 2026-11-10) → 1.3.0 (published 2026-11-13), between the registry lists of 2026-11-13 and 2026-11-14.

No release note: the registry entry links no GitHub repository.

Source: the official MCP Registry list on 2026-11-13 and on 2026-11-14; release notes from the GitHub Releases API, checked 2026-11-14.

What it is

What does this server offer?

Observed inventory
26tools
0resources
0prompts

None of its 26 tools are described as changing anything. For 26 the reading was uncertain, so no mark is shown.

  • search_coinson 9 other servers

    “Lists coins on Souvenir, searched and sorted.”

    Publisher declares: read-only yes · open-world no

    6 inputs
    • qstring“Search: a coin's name or ticker ($ optional), its prize's name, or the start of its mint.”
    • sortstring“pot: the largest open pot first.”
    • venuestring“Only coins trading there: pump.fun, Meteora or Bags.”
    • nsfwboolean“true to list coins whose prize is adult (NSFW) too; left out by default.”
    • limitinteger“Coins a page.”
    • cursorstring“The last page's nextCursor.”
  • “One coin by its mint address, as search_coins lists it: mint, symbol, name, image, venue (pump, meteora or bags), origin (launched on Souvenir or brought), mode (full: its rounds draw an item; draws:…”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • mintstringrequired“The coin's mint address (base58).”
  • “A coin's rounds, newest first, 50 a page.”

    Publisher declares: read-only yes · open-world no

    2 inputs, 1 required
    • mintstringrequired“The coin's mint address (base58).”
    • cursorstring“The last page's next.”
  • “One round in full: { round } with its mode, target and pot, its state in words (stateText), and its proof: the holder snapshot's slot, the ticket total, the Merkle root, the drand round and randomnes…”

    Publisher declares: read-only yes · open-world no

    2 inputs, 2 required
    • mintstringrequired“The coin's mint address (base58).”
    • numberintegerrequired“The round's number.”
  • sign_in_challenge

    “The first step of launching: { id, message, expiresAt } for your Solana wallet.”

    Publisher declares: read-only no · destructive no · open-world no

    1 input, 1 required
    • walletstringrequired“Your Solana wallet's address (base58): the wallet that will launch, pay and sign.”
  • “The signed challenge: { token, wallet, expiresAt }, a token for an hour (then sign in again) that the launch tools take as token, or that the request sends as Authorization: Bearer <token>.”

    Publisher declares: read-only no · destructive no · open-world no

    2 inputs, 2 required
    • idstringrequired“The id sign_in_challenge gave.”
    • signaturestringrequired“The wallet's ed25519 signature of the message, base64 (64 bytes).”
  • launch_options

    “What launching takes now for your wallet, as the site's launch form reads it: allowed and its reason, venues (meteora: Souvenir's own curve; pump: pump.fun), feeLevels and shareLevels in basis points…”

    Publisher declares: read-only yes · open-world no

    1 input
    • tokenstring“The token sign_in gave.”
  • search_prizes

    “Prizes a coin can be launched with now, from Souvenir's catalogue: { prizes, total, next }.”

    Publisher declares: read-only yes · open-world no

    4 inputs
    • qstring“Words of the prize's name, brand or store.”
    • kindstring“Only one kind: goods (store items), services, gift (gift cards), stars (Telegram Stars), packs, graded (graded cards), nft (Solana NFTs), evm (Ethereum NFTs), …”
    • limitinteger“Prizes a page.”
    • offsetinteger“The last page's next.”
  • shopper_sample

    “For a shopper coin, one that picks its own prizes: what a shopper with this brief and price band would start with, as the site's launch form asks it: { id, prize: { name, title, image, priceUsd, stor…”

    Publisher declares: read-only no · destructive no · open-world no

    4 inputs, 3 required
    • tokenstring“The token sign_in gave.”
    • briefstringrequired“What the coin should like, in a line or two of plain words: no links, @handles or $tickers.”
    • minUsdnumberrequired“The band's cheapest price, in dollars.”
    • maxUsdnumberrequired“The band's dearest price, in dollars: at most 10 times the cheapest.”
  • prepare_launchon 2 other servers

    “Prepares your launch, as the site's launch form does (the same checks, fees and rules): stores the picture and the coin's metadata and answers { mint, transaction, summary }, the transaction base64 f…”

    Publisher declares: read-only no · destructive no · open-world yes

    30 inputs, 4 required
    • tokenstring“The token sign_in gave.”
    • namestringrequired“The coin's name.”
    • symbolstringrequired“Its ticker: letters and digits.”
    • descriptionstring
    • imageUrlstringrequired“The coin's picture: an https address on a public host; png, jpg, gif or webp, at most 4 MB.”
    • bannerUrlstring“A banner for the top of its page, optional: https; png, jpg or webp, at most 3 MB, three times as wide as tall, at least 600 px wide.”
    • linksobject“https links; without a website, the coin's Souvenir page.”
    • venuestring“meteora: Souvenir's own curve (it needs feeBps).”
    • feeBpsinteger“The trading fee in basis points (meteora); on a BTC pump.fun launch, its creator fee, one of launch_options pump.feeLevels.”
    • shareBpsintegerrequired“The fee's share for the prize pot, in basis points (7500 by default on the site); 0 is a coin with no prize.”
    • skinstring“The prize: an id from search_prizes, or a CS2 skin's market name.”
    • casestring“One of Souvenir's cases instead, <id>@<version>.”
    • basketarray“A basket of prizes instead: round 1 draws the first, each draw picks the next.”
    • basketOddsarray“Each basket prize's chance in whole percents, in the basket's order (equal without).”
    • ladderarray“A prize ladder instead: 2 to 10 places in order, 1st first, each its own winner at every draw (each worth no more than the place above).”
    • curatorobject“A shopper instead: the id of a sample pick this wallet asked for (shopper_sample).”
    • launchWindowboolean“meteora: the fee starts at 50% and falls to the coin's over 60 seconds.”
    • volatilityboolean“meteora: Meteora's dynamic fee on top of the base fee.”
    • ticketsobject“How a holder's balance turns into draw tickets; without it, capped at 3% of the supply a wallet.”
    • holdHoursinteger“How long a coin must be held before it counts in a draw.”
    • stakingboolean“Staking open from the start.”
    • charityobject“A charity coin: { address, name, url?, pledgeBps?, rounds?, ship?, variant?”
    • shareWithobject“Souvenir's curve only: a tenth, a quarter or half of what the coin earns its creator goes to this wallet each time the creator is paid, fixed for good once the…”
    • shieldboolean“The launch shield, on a BTC pump.fun launch while launch_options says pump.shield.on.”
    • firstBuyLamportsstring“A first buy in lamports (Souvenir's curve, or a SOL pump.fun launch).”

    and 5 more not listed here.

  • submit_launch

    “Your wallet's signed launch: Souvenir checks it is the prepared one (your wallet may only add its compute budget or guard instructions), adds the coin's own signature and sends it.”

    Publisher declares: read-only no · destructive no · open-world yes

    4 inputs, 1 required
    • tokenstring“The token sign_in gave.”
    • mintstringrequired“The mint prepare_launch answered.”
    • transactionsarray“The transaction prepare_launch answered, signed by your wallet, base64.”
    • transactionstring“The same, as one string instead of a list.”
  • launch_statuson 3 other servers

    “Where your launch stands, as the site's page follows it: { status, mint } with status pending (ask again in a few seconds), split (a pump.fun launch landed: transaction is the second approval, the sp…”

    Publisher declares: read-only no · destructive no · open-world yes

    3 inputs, 1 required
    • tokenstring“The token sign_in gave.”
    • mintstringrequired“The coin's mint address (base58).”
    • signaturestring“The signature submit_launch answered; without it, the one Souvenir recorded.”
Show 14 more tools
  • submit_split

    “The split launch_status handed over, approved by your wallet: either the signature of the transaction your wallet signed and sent itself, or the signed transaction (base64) for Souvenir to send.”

    Publisher declares: read-only no · destructive no · open-world yes

    4 inputs, 1 required
    • tokenstring“The token sign_in gave.”
    • mintstringrequired“The coin's mint address (base58).”
    • signaturestring“The split's signature, sent by your wallet.”
    • transactionstring“Or the split signed by your wallet, base64, for Souvenir to send.”
  • “What a buy or a sell of a Souvenir coin gives now, as the coin's page quotes it: { out, minOut, feeLamports, partial, venue }.”

    Publisher declares: read-only yes · open-world yes

    5 inputs, 3 required
    • mintstringrequired“The coin's mint address (base58).”
    • sidestringrequired“buy: spend SOL for the coin.”
    • amountstringrequired“What you give, in whole units, as a string: lamports for a buy (1 SOL is 1000000000), the coin's raw units for a sell (Souvenir's and pump.fun's coins have 6 d…”
    • slippageBpsinteger“The most the price may move against you before the trade refuses, in basis points (300 is 3%, the site's default).”
    • paystring“What a coin paired with $SOUVENIR is paid in (a sell: what it receives): sol, the default, or souvenir.”
  • “The trade's transaction for your wallet to sign, as the coin's page builds it: { transaction, out, minOut }, the transaction base64 (unsigned, version 0, paid by your wallet).”

    Publisher declares: read-only yes · open-world yes

    6 inputs, 4 required
    • mintstringrequired“The coin's mint address (base58).”
    • sidestringrequired“buy: spend SOL for the coin.”
    • amountstringrequired“What you give, in whole units, as a string: lamports for a buy (1 SOL is 1000000000), the coin's raw units for a sell (Souvenir's and pump.fun's coins have 6 d…”
    • slippageBpsinteger“The most the price may move against you before the trade refuses, in basis points (300 is 3%, the site's default).”
    • paystring“What a coin paired with $SOUVENIR is paid in (a sell: what it receives): sol, the default, or souvenir.”
    • walletstringrequired“Your Solana wallet's address (base58): it pays, signs and receives.”
  • send_transactionon 1 other server

    “Sends a transaction your wallet signed (base64, every signature in place) to Solana, as the site sends what a wallet signs: { signature }.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    1 input, 1 required
    • transactionstringrequired“The transaction build_trade answered (or prepare_launch's devSwap or souvSwap), signed by your wallet, base64.”
  • request_trade

    “For an agent helping a person who holds their own wallet: a link (url) for them to open, see this trade with a fresh quote, and approve it with their own wallet on souvenir.finance.”

    Publisher declares: read-only no · destructive no · open-world no

    4 inputs, 3 required
    • mintstringrequired“The coin's mint address (base58).”
    • sidestringrequired“buy: spend SOL for the coin.”
    • amountstringrequired“What you give, in whole units, as a string: lamports for a buy (1 SOL is 1000000000), the coin's raw units for a sell (Souvenir's and pump.fun's coins have 6 d…”
    • slippageBpsinteger“The most the price may move against the trade, in basis points (300 is 3%): 10 to 1000, 300 by default.”
  • trade_requeston 1 other server

    “How an approval link from request_trade stands: { id, url, state, expiresAt, side, amount, slippageBps, coin, wallet, signature, out }.”

    Publisher declares: read-only yes · open-world no

    1 input, 1 required
    • idstringrequired“The id request_trade answered.”
  • my_wins

    “Your wallet's wins, as the site's prizes page reads them: { wins, link, evmAddress }, the newest first.”

    Publisher declares: read-only yes · open-world no

    1 input
    • tokenstring“The token sign_in gave.”
  • claim_sol

    “Takes a won prize's SOL instead of the prize now, as the prizes page does, through the site's own route for that kind of prize: its share of the prize's worth (my_wins solOffer: 75% for a skin or a c…”

    Publisher declares: read-only no · destructive yes · idempotent no · open-world yes

    4 inputs, 2 required
    • tokenstring“The token sign_in gave.”
    • mintstringrequired“The coin the prize was won on (a win's mint in my_wins).”
    • roundintegerrequired“The round it was won in (a win's number in my_wins).”
    • countrystring“Where you are, optional (a physical item: it shows Souvenir where to ship next).”
  • recent_wins

    “The latest wins on Souvenir, newest first, as the site's Recent winners lists them: { wins }, each with mint, symbol, coinImage, skin (the prize), skinImage, winner, winnerShort, round, at, state, or…”

    Publisher declares: read-only yes · open-world no

    2 inputs
    • nsfwboolean“true to list wins of adult (NSFW) prizes too; left out by default.”
    • limitinteger“Wins a page.”
  • “A coin's holders now, as its page shows them: { slot, total, streak, holdHours, holders }, the 50 with the most draw tickets: owner, amount (the coins held now, raw units), tickets, multiplier (1 to …”

    Publisher declares: read-only yes · open-world yes

    1 input, 1 required
    • mintstringrequired“The coin's mint address (base58).”
  • create_coin_key

    “A coin key for the coins your wallet created, as the coin page's Developers dialog makes one: { key, id, webhookSecret, view }.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world no

    3 inputs, 1 required
    • tokenstring“The token sign_in gave.”
    • namestringrequired“A name for the key, 1 to 60 characters.”
    • webhookUrlstring“Optional: an https address on a public host that gets a signed POST for each step of your coins' rounds.”
  • revoke_coin_key

    “Ends one of your coin keys now, as the coin page's Developers dialog does: { ok }.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    2 inputs, 1 required
    • tokenstring“The token sign_in gave.”
    • idstringrequired“The key's id (create_coin_key's id).”
  • set_coin_mode

    “Your coin's mode from its next round (the round filling keeps its own): full (its rounds draw its prize), draws (each round pays drawSol in SOL to its winner) or prizes (you give prizes from its pot …”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world no

    4 inputs, 2 required
    • coinKeystring“Your coin key (ck_live_…, from create_coin_key).”
    • mintstringrequired“The coin's mint address (base58).”
    • modestringrequired
    • drawSolstring“draws: the SOL each round pays, 0.1 to 100, as a decimal string ("0.5").”
  • award_prize

    “A coin in prizes mode: gives winner an item, bought now from the coin's open pot at its fresh price plus a round's margin, as a round of the coin's: { round }.”

    Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes

    5 inputs, 4 required
    • coinKeystring“Your coin key (ck_live_…, from create_coin_key).”
    • mintstringrequired“The coin's mint address (base58).”
    • winnerstringrequired“The wallet that wins it (base58).”
    • itemstringrequired“The prize: an id from search_prizes.”
    • idempotencyKeystringrequired“Your own id for this award, 1 to 100 letters, digits or symbols: sent again, the same round answers.”

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 2026-11-19.

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

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
97% of 103
Tools with a description
100% of 26
Typical description length
929 characters

The tool set

Counted from the listing

Tools
26
Size of the list
about 11,541 tokens for an agent to load (characters ÷ 4)
Naming
26 of 26 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 26 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 remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-19 (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://souvenir.finance/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "coins": {
      "url": "https://souvenir.finance/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "coins": {
      "type": "http",
      "url": "https://souvenir.finance/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"coins","type":"http","url":"https://souvenir.finance/mcp"}'
Claude Code
claude mcp add --transport http coins https://souvenir.finance/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "coins": {
      "type": "streamableHttp",
      "url": "https://souvenir.finance/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "coins": {
      "httpUrl": "https://souvenir.finance/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.coins]
url = "https://souvenir.finance/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "coins": {
      "url": "https://souvenir.finance/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://souvenir.finance/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • 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; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). 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.

What do the published files and outside lists say?

Read as text · nothing run · no tool called

Package files

  • MCP SDK in the package files. Not read yet: added with the next daily run.
  • Build workflow. Not read yet: added with the next daily run.

Outside lists

  • CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-14. This product uses the NVD API but is not endorsed or certified by the NVD.
  • GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-14. GitHub Advisory Database, CC BY 4.0
  • Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-14. Source: read 2026-11-14.
  • Cline marketplace. Not in the Cline marketplace on 2026-11-14. Source: read 2026-11-14.

Own host

Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint souvenir.finance/mcpSession openedmatchesour test · 2026-11-19
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-19

Tool list changes

Our reads compared · no tool called

Hosted endpoint souvenir.finance/mcp

2 of 2 comparisons between consecutive reads showed a change (3 reads, 2026-11-12 to 2026-11-19; versions 1.2.0 to 1.3.0).

Last change seen between our reads on 2026-11-14 (version 1.3.0) and 2026-11-19 (version 1.3.0). Changed without a new version: both reads list version 1.3.0.

Added (1):

shopper_sample

Changed (18):

award_prize: descriptionbuild_trade: description, input schemaclaim_sol: descriptionget_coin: descriptionlaunch_options: descriptionlaunch_status: descriptionmy_wins: descriptionprepare_launch: description, input schemaquote_trade: description, input schemarequest_trade: descriptionsearch_coins: descriptionsearch_prizes: descriptionsend_transaction: description, input schemaset_coin_mode: descriptionsign_in: descriptionsign_in_challenge: descriptionsubmit_launch: descriptionsubmit_split: description

Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-19 is not known yet. No tool was called. How it is compared

Choosing

Record checks

Public records · not a safety rating

1 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.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
  • 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 2026-11-14. 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, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about finance.souvenir/coins

Answered from the data above

Who publishes finance.souvenir/coins?

The registry ties the namespace finance.souvenir to the domain souvenir.finance; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.

Does finance.souvenir/coins need an API key or sign-in?

It opened a session without any credential on 2026-11-19. The registry entry declares no required credential; no declaration is not a guarantee.

Has finance.souvenir/coins 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. ProtocolProbe publishes no security verdict for a named server.

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.

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.

The 18 checks at a glanceour test · 2026-11-19
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. 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. These 18 checks are separate from the record checks at the top of this page, which read public records only.

Exercised · 2
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants 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
    ssrf
    Checks 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks 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-data
    Checks 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-boundary
    Checks 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, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks 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-hiding
    Checks 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-redirect
    Checks 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-deputy
    Checks 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 · 4
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks 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-validation
    Checks 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-scheme
    Checks 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, 2026-11-19, 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.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,199 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 26 tools, 0 resources, 0 prompts.
  4. 4,435 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.

TopicAI-classified
pending: added at the next monthly refresh
listed 2026-11-14; not classified yet
Pricing modelAI-classified
pending: added at the next monthly refresh
the website is not read yet
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-11-14
MCP capability
tools
our test · 2026-11-19
Transport
streamable HTTP
registry · 2026-11-14
Required credentials
none declared
registry · 2026-11-14 · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-11-14
Lifecycle status
registry · 2026-11-14
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type · 2026-11-14

“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. “finance.souvenir/coins: MCP server record.” Data checked 2026-11-19. https://protocolprobe.com/mcp/servers/finance.souvenir/coins

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: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/finance.souvenir/coins)](https://protocolprobe.com/mcp/servers/finance.souvenir/coins)

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, except for a server whose operator has claimed it and given permission (that server's page says so).

Write to hello@protocolprobe.com · corrections log · methodology