Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.ciinkwia/agent-tool-finder

REMOTE · CLINK-LITHIUM-VAULT.FLY.DEV

Free search across ~35,000 agent tools (x402 bazaar + MCP registry) by plain-language need.

0 this week 23 Trust /100

Last scanned (23 hours ago)

Scores higher than 7% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
  • Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
  • Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified

Unverified: 5 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

What we tested

Checks we ran (5)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport

Checks we could not complete (6)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  • Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
  • Tool coverage in Tool Coverage (scores 0 for this)Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
  • Tool safety in Tool Safety (scores 0 for this)Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
  • Capabilities in Capabilities (scores 0 for this)Capabilities not yet verified: we couldn't read the endpoint's capabilities.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 28 Oct 26 −49
    • Endpoint reachability: reachable → not serving MCP ▼ security
    • Stability: fail → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
  • 25 Oct 26 0
    • Tool “token_verdict” rewrote its description, which is the text the model reads security
    • Tool “x_profile” rewrote its description, which is the text the model reads security
    • Schema quality: 150 → 171 ▼ functional
    • New tool “token_holders” functional
    • New tool “token_kol_calls” functional
    • New tool “token_new_launches” functional
    • New tool “token_smart_money” functional
    • New tool “token_verdict_batch” functional
    • New tool “token_whales” functional
    • New tool “wallet_activity” functional
    • New tool “wallet_pnl” functional
    • New tool “wallet_verdict” functional
    • “token_verdict” added an optional parameter “chain” cosmetic
    • “token_verdict” reworded the description of “address” cosmetic
  • 24 Oct 26 −4
    • Stability: pass → fail ▼ security
  • 23 Oct 26 76
    • New tool “web_answer” functional
  • 20 Oct 26 0
    • A breaking change shipped without a version bump: still 0.2.0 ▼ security
    • Tool “pm_closing” was removed ▼ security
    • Tool “pm_gaps” was removed ▼ security
    • Tool “pm_odds” was removed ▼ security
    • Tool “pm_resolved” was removed ▼ security
    • Tool “pm_search” was removed ▼ security
    • Tool “pm_sentiment” was removed ▼ security
    • Tool “pm_ticker_events” was removed ▼ security
    • Tool “pm_watch” was removed ▼ security
    • Tool “web_answer” was removed ▼ security
    • Schema quality: 3877 → 2529 ▲ functional
  • 15 Oct 26 0
    • A breaking change shipped without a version bump: still 0.2.0 ▼ security
    • Tool “buy_credits” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “pdf_text” rewrote its description, which is the text the model reads security
    • Tool “pm_closing” rewrote its description, which is the text the model reads security
    • Tool “pm_gaps” rewrote its description, which is the text the model reads security
    • Tool “pm_odds” rewrote its description, which is the text the model reads security
    • Tool “pm_resolved” rewrote its description, which is the text the model reads security
    • Tool “pm_search” rewrote its description, which is the text the model reads security
    • Tool “pm_sentiment” rewrote its description, which is the text the model reads security
    • Tool “pm_ticker_events” rewrote its description, which is the text the model reads security
    • Tool “pm_watch” rewrote its description, which is the text the model reads security
    • Tool “sec_insider” rewrote its description, which is the text the model reads security
    • Tool “ticker_brief” rewrote its description, which is the text the model reads security
    • Tool “token_verdict” rewrote its description, which is the text the model reads security
    • Tool “translate_text” rewrote its description, which is the text the model reads security
    • Tool “web_answer” rewrote its description, which is the text the model reads security
    • Tool “x_digest” rewrote its description, which is the text the model reads security
    • Tool “x_leads_deep” rewrote its description, which is the text the model reads security
    • Tool “x_list” rewrote its description, which is the text the model reads security
    • Tool “x_person” rewrote its description, which is the text the model reads security
    • Tool “x_profile” rewrote its description, which is the text the model reads security
    • Tool “x_search” rewrote its description, which is the text the model reads security
    • Tool “x_ticker_pulse” rewrote its description, which is the text the model reads security
  • 7 Oct 26 0
    • Tool “token_verdict” rewrote its description, which is the text the model reads security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://clink-lithium-vault.fly.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.fly.dev CN=YE1,O=Let's Encrypt,C=US 20 Oct 2026 18 Jan 2027 ECDSA 256 ECDSA-SHA384 5e6e25e6df778e81cd07b85fc9f12d4df7d
SANs: *.fly.dev
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of clink-lithium-vault.fly.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
fly.dev. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Inconclusive

We could not reach the endpoint well enough to judge its authorisation posture.

Result Inconclusive
HTTP status 503

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://clink-lithium-vault.fly.dev/mcp HTTP error 503
http (plaintext) http://clink-lithium-vault.fly.dev/mcp HTTPS enforced 301 https://clink-lithium-vault.fly.dev/mcp
MCP tools · 27 exposed · ~4,448 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
agent_market_stats ~66

Get current size and shape of the agent tool market: how many paid x402 endpoints and MCP servers exist, how many have real paying users, and total measured spend over the last 30 days. Useful for deciding whether a capability is well supplied before you build it yourself. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

credits_balance ~37

Check the shop-credits balance for the key on this connection (Authorization: Bearer ck_live_… or X-Clink-Key). Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

find_agent_tools ~251

Find an API, data source, or MCP server that can do something you cannot do on your own. Searches 35,000+ agent-callable tools: ~14,000 paid x402 endpoints and ~21,000 MCP servers, in one place. Use it whenever you need outside data or a capability you lack — web search, onchain and crypto data, company or people lookup, scraping, maps, weather, documents, financial data, travel, and more. Returns what each tool does, how to call or install it, and what it costs. Free to use.

NameTypeReqDescription
kindstring–Optional. 'x402' for paid pay-per-call HTTP endpoints, 'mcp' for installable MCP servers. Omit to search both.
limitnumber–Optional. Max results, 1-25. Default 8.
max_price_usdnumber–Optional. Only return paid endpoints at or below this price per call.
needstringyesWhat you need, in plain language. Describe the capability or data, not a tool name. Example: 'historical lithium spodumene prices' or 'check if a wallet holds an NFT'.

No output schema declared.

No examples provided.

pdf_text ~102

Convert a public PDF to plain text — full extracted text in one call, up to 25MB / 500k chars, with page count and a likely_scanned flag (text-based PDFs only, no OCR). Costs $0.01 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
urlstringyespublic http(s) URL of a PDF file

No output schema declared.

No examples provided.

request_agent_tool ~173

Ask clink's shop to BUILD a tool or data source that nobody sells yet. Use this right after find_agent_tools comes back unsatisfied. clink reads every request the same day; buildable asks ship as pay-per-call x402 endpoints, usually within a week. Returns a request id and a status URL; pass `notify` (email or https webhook) to be told the moment it ships.

NameTypeReqDescription
budget_usdnumber–Optional. What one call is worth to you, in USD — helps clink price it.
notifystring–Optional. An email address or https webhook URL to ping when it ships (or is declined).
wantstringyesWhat you need, plain language, 3-500 chars. Describe the data or capability and how you'd call it.

No output schema declared.

No examples provided.

sec_insider ~165

SEC Form 4 insider trading for one US stock ticker — every insider buy/sell/grant/gift in the window (name, role, date, code, shares, price, shares owned after, filing URL) plus open-market buy vs sell totals. Source: SEC EDGAR. Facts only — this is not investment advice, a price target, or a buy/sell/hold signal. Costs $0.01 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
daysnumber–1-365, default 90
limitnumber–1-25, default 25
tickerstringyese.g. AAPL

No output schema declared.

No examples provided.

send_feedback ~246

Report a bug, missing feature, wrong data, or a slow call on clink's shop — for a call you already made, not a new capability request (use request_agent_tool for that). Read the same day; if it's a real bug it gets fixed and you're told. Free.

NameTypeReqDescription
kindstringyes–
notifystring–Optional. An email address or https webhook URL to ping when it's fixed.
receipt_idstring–Optional. The rcpt_… id from the receipt block of the paid call you're reporting — links this to the exact call.
request_urlstring–Optional. The exact call that went wrong, including query params.
routestring–Optional. The endpoint path you called, e.g. /x/search.
tx_or_buyerstring–Optional. Your wallet address or a transaction hash for the call, if you have it — helps link this to the actual failed call.
wantedstring–Optional. What you expected/wanted instead, up to 2000 chars.
what_happenedstringyesWhat happened, 3-2000 chars.

No output schema declared.

No examples provided.

ticker_brief ~116

One-call US stock ticker brief — X/Twitter activity (24h), SEC Form 4 insider activity (90d), and the latest 8-K, bundled. Each section fails independently. Facts only — this is not investment advice, a price target, or a buy/sell/hold signal. Costs $0.04 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
tickerstringyese.g. NVDA

No output schema declared.

No examples provided.

token_holders ~206

Who owns a token — top 10 holders (percent, contract, locked, tag), holder count, top-10 share and a low/medium/high concentration label, creator wallet and share, LP locked %, and on Base the first 25 buyers (bought from a pool or received, when, how much, still holding, share of supply now). Chains: base, ethereum, bsc, arbitrum, polygon, optimism, avalanche, solana. 404/free if the token is unknown; 503/free if every source is down. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyestoken contract address (0x... on EVM chains, base58 mint on solana)
chainstring–base (default), ethereum, bsc, arbitrum, polygon, optimism, avalanche or solana

No output schema declared.

No examples provided.

token_kol_calls ~227

Crypto KOL tracker — send a token contract, get the big X/Twitter accounts posting about it, ranked by followers: handle, followers, verified, post count, first post time, best post, strong (exact address) or weak (cashtag only) match; plus kol_count, total_reach, first_call_at, a buzz label (none/low/rising/hot) and DexScreener price change. 8 chains incl. Base and Solana. 404/free if no account over the follower floor posted. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyestoken contract address (0x... on EVM chains, base58 mint on Solana)
chainstring–Optional, default base
min_followersstring–Optional follower floor, 1000-1000000 (default 10000)
windowstring–Optional, default 24h

No output schema declared.

No examples provided.

token_new_launches ~243

New token launches with a safety verdict on each — the newest DEX pools on a chain (base default; ethereum, bsc, arbitrum, polygon, optimism, avalanche, solana), every token scored 0-100 and labeled safe / caution / risky / avoid from honeypot, buy/sell tax, mint, owner-can-change-balance, proxy, LP lock and top-10 holder flags, plus liquidity, 24h volume, buys/sells and age. A token whose check did not finish comes back checked:false, never guessed. 404/free if no pool in the window. Costs $0.05 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
chainstring–base (default), ethereum, bsc, arbitrum, polygon, optimism, avalanche, solana
limitnumber–1-20, default 10
min_liquidity_usdnumber–0-1000000, default 1000
windowstring–default 1h

No output schema declared.

No examples provided.

token_smart_money ~174

Smart-money traders on a token — the 10 wallets that traded the most USD on it in the window (buys, sells, net, trades), each graded smart / profitable / mixed / losing from its own 30-day realized PnL and win rate (Base only for now), plus smart_lean: accumulating / distributing / mixed / none. 404/free if no trades in the window; 503/free if a data source is down. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyestoken contract (0x...) or Solana mint address
chainstring–default base
windowstring–default 24h

No output schema declared.

No examples provided.

token_verdict ~197

Token safety check — send a token contract, get a verdict (safe / caution / risky / avoid), a 0-100 score, risk level, red and green flags, a short summary, metrics (holders, top-10 share, LP locked, liquidity, 24h volume, pair age, taxes), a post-ready card and X/Twitter post counts. Checks honeypot, taxes, mint/pause/blacklist/fee powers, proxy, renounced owner. 8 chains. 404/free if no source knows the token; 503/free if the sources are down. Costs $0.01 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyestoken contract (0x... on EVM chains, base58 mint on Solana)
chainstring–default base

No output schema declared.

No examples provided.

token_verdict_batch ~207

Token safety verdicts for up to 25 tokens in one call — one row per token: verdict (safe/caution/risky/danger), score 0-100, risk level, flags (honeypot, sell tax, mintable, hidden owner, holder concentration, low liquidity), liquidity, holders, top-10 share, price; plus counts per verdict and a not_found list. Base by default; also ethereum, bsc, polygon, arbitrum, optimism, avalanche, solana. 404/free if no token is known; 503/free if the sources are down. Costs $0.10 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressesstringyes1-25 comma-separated token contract addresses
chainstring–base (default), ethereum, bsc, polygon, arbitrum, optimism, avalanche, solana

No output schema declared.

No examples provided.

token_whales ~251

Whale trades on any token — the latest big buys and sells (time, side, USD, token amount, price, wallet, tx, pool, dex) newest first, plus the top 10 net buyer and top 10 net seller wallets, whale buy/sell/net USD totals and a net_buying / net_selling / mixed lean. Top 3 pools by liquidity. Chains: base, ethereum, bsc, arbitrum, polygon, optimism, avalanche, solana. 404/free if no trade above the floor; 503/free if the trade source is down. Costs $0.01 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyesToken contract (0x + 40 hex on EVM chains) or Solana mint
chainstring–default base
limitnumber–trades returned, 1-100, default 25
min_usdnumber–smallest trade to count in USD, 100-1000000, default 5000
windowstring–default 24h

No output schema declared.

No examples provided.

translate_text ~129

Translate text — up to 2,000 chars, any language pair, source auto-detected when omitted. Returns clean JSON: detected source language + full translation. Costs $0.01 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
source_langstring–optional; auto-detected when omitted
target_langstringyeslanguage to translate into, e.g. 'English', 'es'
textstringyestext to translate, up to 2,000 chars

No output schema declared.

No examples provided.

wallet_activity ~202

What a Base wallet bought, sold and moved lately — its token + ETH moves newest first (time, in/out, token, amount, USD value, counterparty, tx, swap flag), a per-token in/out/net table sorted by net USD, newly picked-up tokens, USD in/out totals, swap count and top 5 counterparties. Facts only — this is not investment advice, a price target, or a buy/sell/hold signal. 404/free if no moves in the window; 503/free if the chain read is down. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyes0x-prefixed Base wallet address
daysnumber–1-30, default 7
limitnumber–moves listed, 1-100, default 50

No output schema declared.

No examples provided.

wallet_pnl ~175

Trader report card for one Base wallet — realized profit in USD, win rate, closed positions, open positions (value now, cost basis, unrealized P&L), top 5 wins and losses, an unpriced_moves count, and a grade (smart / profitable / mixed / losing / not_enough_history) with its rule. 400/free for a contract address; 404/free if the wallet made no swap in the window; 503/free if the chain read is down. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyes0x-prefixed Base wallet address (not a contract)
daysstring–window in days, default 30

No output schema declared.

No examples provided.

wallet_verdict ~187

Who is behind a Base wallet — kind (wallet/contract, token, proxy), Basename, age, tx count, ETH + USDC balance, first funder (amount, when, its age and flags), tokens it launched, phishing/mixer/sanction/scam flags, activity label, and a trusted/normal/caution/high_risk verdict with a 0-100 trust score, red/green flags and the rule that set it. 404/free if the address was never used; 503/free if the chain read is down. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
addressstringyes0x-prefixed Base address (wallet or contract)
chainstring–Optional; only base in this version

No output schema declared.

No examples provided.

web_answer ~182

Cited web answer — ask a question, get a short answer built from a live Exa neural search + page read + AI synthesis in one call: verbatim quotes, source URLs, confidence. Not a raw SERP. Optionally scope by since: (YYYY-MM-DD) or up to 5 domains. Costs $0.03 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
domainsarray–optional, up to 5 hostnames, e.g. ['nytimes.com']
max_sourcesnumber–optional, 3-8, default 5
questionstringyes3-500 char plain-language question
sincestring–optional YYYY-MM-DD — only sources published on/after this date

No output schema declared.

No examples provided.

x_digest ~97

X/Twitter trend digest — live tweet search PLUS an AI-written summary: sentiment, key themes, driving accounts, notable posts. Same query syntax as x_search. Costs $0.05 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
querystringyesAdvanced X search query, e.g. '#bitcoin min_faves:50'

No output schema declared.

No examples provided.

x_leads_deep ~172

X/Twitter deep lead finder — one call does the whole search -> profile -> contact chain: searches up to 4 pages, finds the PEOPLE behind the posts, enriches the top 10-15 with their own website (emails, LinkedIn, GitHub) and clusters them with a one-line why-they-match each. Recruiting, B2B prospecting, cofounder/investor search. Costs $0.20 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
maxstring–Optional. How many people to enrich, 1-15 (default 10).
querystringyesAdvanced X search query, e.g. '"open to work" rust'

No output schema declared.

No examples provided.

x_list ~150

X/Twitter watchlist — 2-50 handles in one call, their combined recent tweets newest first, deduped, per-handle counts and a since-cursor for only-what's-new next time. No from:-OR-splitting. Costs $0.05 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
handlesstringyescomma or space separated handles, e.g. 'elonmusk,naval,balajis'
limitstring–1-100, default 40
sincestring–optional ISO timestamp or tweet id cursor

No output schema declared.

No examples provided.

x_person ~131

X/Twitter person lookup — enriched PERSON CARD for a lead/recruiting/sales agent: name, role, company, what they work on, topics, seniority guess, and contact routes (emails actually found on their site/bio, LinkedIn, GitHub, X DM-open flag), plus non-LLM stats (followers, account age, posts/week). Costs $0.15 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
usernamestringyesX handle, e.g. naval

No output schema declared.

No examples provided.

x_profile ~90

X/Twitter profile lookup — display name, bio, follower/following counts, verified status, location, join date, profile URL for one handle. Costs $0.01 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
usernamestringyesX handle, e.g. elonmusk

No output schema declared.

No examples provided.

x_search ~117

Live X/Twitter search for AI agents — advanced search syntax (from:user, "exact phrase", #hashtag, since:/until:, min_faves:, lang:). Up to 20 newest tweets with author, likes, retweets, views, URL. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
querystringyesAdvanced X search query, e.g. 'from:elonmusk lithium'

No output schema declared.

No examples provided.

x_ticker_pulse ~155

X/Twitter activity for one US stock ticker — post volume vs the prior window, top posts, most active accounts, keyword topic flags (earnings, guidance, lawsuit, SEC investigation, recall, M&A, layoffs, upgrade/downgrade, short report, dividend, buyback, CEO). Facts only — this is not investment advice, a price target, or a buy/sell/hold signal. Costs $0.02 per call, paid from clink's shop credits (an existing key; new top-ups are paused). A failed or empty call is free.

NameTypeReqDescription
tickerstringyese.g. TSLA or $TSLA
windowstring–default 24h

No output schema declared.

No examples provided.

Install

How do I install the io.github.ciinkwia/agent-tool-finder MCP server?

io.github.ciinkwia/agent-tool-finder is a hosted endpoint at https://clink-lithium-vault.fly.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · clink-lithium-vault.fly.dev

# add to Claude Code
claude mcp add --transport http ciinkwia-agent-tool-finder 'https://clink-lithium-vault.fly.dev/mcp'
Common questions

What is the io.github.ciinkwia/agent-tool-finder MCP server?

io.github.ciinkwia/agent-tool-finder is an MCP server listed in the public MCP registry as io.github.ciinkwia/agent-tool-finder. Free search across ~35,000 agent tools (x402 bazaar + MCP registry) by plain-language need. This page covers its hosted endpoint (https://clink-lithium-vault.fly.dev/mcp).

Is the io.github.ciinkwia/agent-tool-finder MCP server safe to use?

io.github.ciinkwia/agent-tool-finder scores 23 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.ciinkwia/agent-tool-finder MCP server expose?

io.github.ciinkwia/agent-tool-finder exposes 27 tools: find_agent_tools, agent_market_stats, request_agent_tool, send_feedback, x_search, and 22 more. Their descriptions and schemas cost roughly 4,448 tokens of context every time the server is loaded.

Does the io.github.ciinkwia/agent-tool-finder MCP server require authentication?

Its publisher declares no required credentials for io.github.ciinkwia/agent-tool-finder. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

Is the io.github.ciinkwia/agent-tool-finder MCP server still maintained?

io.github.ciinkwia/agent-tool-finder is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the io.github.ciinkwia/agent-tool-finder MCP server?

VerifyMCP ran 5 checks on io.github.ciinkwia/agent-tool-finder, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 1 more. 6 items could not be completed, a gap on our side rather than a finding about io.github.ciinkwia/agent-tool-finder: Authorization, Schema quality, Stability, Tool coverage and 2 more. 5 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.