tokensift
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tokensift Check if 0xABC... is a honeypot on Base"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tokensift
Read-only token due-diligence over keyless public APIs, as one Python package that is both an importable library and a stdio MCP server. Six tools, one envelope, no trading, no secrets.
Tool | Upstream | Chains |
| honeypot.is buy/sell simulation | ethereum, bsc, base |
| rugcheck.xyz risk report | solana |
| DexScreener search | all |
| DexScreener pools for a token | ethereum, bsc, base, solana |
| DexScreener pair snapshot | ethereum, bsc, base, solana |
| Jupiter Price v3 (lite host) | solana |
Every call returns the same envelope (also each tool's outputSchema):
{"ok": true, "source": {"provider": "dexscreener", "url": "…exact GET…", "chain": "solana"},
"fetched_at": "2026-09-06T12:00:00Z", "cache": {"hit": false, "ttl_s": 30},
"summary": {…}, "raw": null, "raw_truncated": false, "error": null}On failure ok is false, summary is null, and error carries type (invalid_input | not_found | rate_limited | upstream_unavailable | upstream_changed), message, optional retry_after_s, and advice written for the model. The MCP tool returns the same envelope with isError=true.
Library
from tokensift import Tokensift
async with Tokensift() as ts:
env = await ts.honeypot_check("base", "0x…")
if env.ok:
print(env.summary["is_honeypot"], env.summary["sell_tax"])Related MCP server: VetAgent
MCP server
uvx --from /path/to/tokensift tokensift-mcp # stdioSee docs/REGISTRATION.md for Claude Code, Codex CLI, and Gemini CLI entries and the Inspector smoke test.
Behavior that matters
Validation before network: chain aliases (
eth,1,bnb,56,8453,sol) and address formats are checked first; bad input never hits an upstream.Per-provider token buckets (
TOKENSIFT_RPM_*). When a bucket is empty the call waits up toTOKENSIFT_LIMITER_WAIT_S(5 s) and then returnsrate_limitedwithretry_after_s.rate_limitedandupstream_unavailableare never cached;invalid_inputandnot_foundare cached forTOKENSIFT_NEG_CACHE_TTL_S(10 s).Successful responses are cached for
TOKENSIFT_CACHE_TTL_S(30 s) keyed by provider, endpoint, and normalized params.One retry on 429/502/503/504 honoring
Retry-After, capped at 5 s. Timeouts and 401/403 becomeupstream_unavailable(403 advice names the datacenter-IP possibility).rawis returned only withverbose=true, capped atTOKENSIFT_RAW_MAX_BYTES(32 kB) withraw_truncated=truewhen cut.Logging goes to stderr only; stdout is the MCP wire.
Dual-era: the server answers both a legacy
initializehandshake and modern2026-07-28per-request metadata (tested over a real pipe).
Development
uv sync
uv run pytest # unit + client + server + contract + stdio (no network)
uv run pytest -m live # one real call per upstream; run weekly
uv run python scripts/record_fixtures.py # refresh recorded upstream fixtures
npx -y @modelcontextprotocol/inspector --cli ./scripts/serve-stdio.sh --method tools/list # flag-free launcher: the inspector cli eats `--from`Stack (pinned 2026-09-06): fastmcp>=4.0,<4.1 on mcp 2.x (spec 2026-07-28), httpx2, pydantic-settings, aiolimiter, cachetools. Python 3.12 via uv.
T0 spike findings (2026-09-06)
fastmcp.tools.ToolResult(content, structured_content, meta, is_error)acceptsis_errorwith structured content, so errors are returned as results, never raised (a raised exception becomes a JSON-RPC error inmcp2.x).mcp.server.runnerdrivesserve_dual_era_loop; a legacyinitializeis handled inline and negotiated fromHANDSHAKE_PROTOCOL_VERSIONS.tests/test_stdio.pyproves both handshakes over a pipe.The
Envelopefieldokforbids a classmethod of the same name; factories areEnvelope.success/Envelope.failed.MCP Inspector CLI v2 parses flags anywhere on its command line, so a target like
uvx --from … tokensift-mcploses--fromand reports "Connection closed".scripts/serve-stdio.shis a flag-free launcher for the Inspector; the three CLIs pass args through correctly and useuvxdirectly.
Available Tools
6 toolsdex_pairDexScreener pair snapshotARead-onlyIdempotent
live snapshot of one dexscreener pair: price, liquidity, fdv, market cap, 24h volume and txns, price change windows, project links and boosts. chains: chain id or alias; supported: ethereum (aliases: eth, 1); bsc (aliases: bnb, 56); base (aliases: 8453); solana (aliases: sol). not_found means no such pair on that chain. verbose=true adds the raw payload.
Inputs: chain (required), pair_address (required), verbose. Returns: ok, raw, cache, error, +4 more
dex_searchDexScreener searchARead-onlyIdempotent
search dexscreener by ticker, name, token address or pair address and return candidate pairs in upstream relevance order with chain, dex, price, liquidity, fdv, 24h volume and txns, and pair age. tickers are ambiguous: confirm identity by contract address (dex_token_pairs / dex_pair) before any safety check. limit 1-30 (default 10). verbose=true adds the raw payload.
Inputs: query (required), limit, verbose. Returns: ok, raw, cache, error, +4 more
dex_token_pairsDexScreener pools for a tokenARead-onlyIdempotent
list dexscreener pools for one token contract on one chain, sorted by liquidity descending, with price, liquidity, fdv, volume, txns and pair age. chains: chain id or alias; supported: ethereum (aliases: eth, 1); bsc (aliases: bnb, 56); base (aliases: 8453); solana (aliases: sol). limit 1-30 (default 20). an empty list means dexscreener does not index the token on that chain. verbose=true adds the raw payload.
Inputs: chain (required), token_address (required), limit, verbose. Returns: ok, raw, cache, error, +4 more
honeypot_checkHoneypot simulation (EVM)ARead-onlyIdempotent
simulate a buy and sell of an evm token via honeypot.is and report is_honeypot, buy/sell/transfer tax, gas, risk flags, pair liquidity, contract open-source/proxy status and holder count. chains: ethereum, bsc, base (chain id or alias; supported: ethereum (aliases: eth, 1); bsc (aliases: bnb, 56); base (aliases: 8453); solana (aliases: sol)); for solana use rugcheck_report. no result means the token has no simulated pair yet. verbose=true adds top holders with supply percentages and the raw payload.
Inputs: chain (required), address (required), verbose. Returns: ok, raw, cache, error, +4 more
jupiter_pricesJupiter prices (Solana)ARead-onlyIdempotent
usd prices for up to 50 solana mints from jupiter price v3 (swap-derived), with liquidity, 24h change and decimals; unknown mints come back with found=false. use as a second price source next to dexscreener. verbose=true adds the raw payload.
Inputs: mints (required), verbose. Returns: ok, raw, cache, error, +4 more
rugcheck_reportRugCheck report (Solana)ARead-onlyIdempotent
fetch rugcheck.xyz's risk report for a solana mint: score and normalised score, named risks with levels, lp locked percentage, token program. verbose=true fetches the full report: mint/freeze authority, top holders with percentages and insider flags, metadata mutability, jupiter verification, and the raw payload. solana only; for evm tokens use honeypot_check.
Inputs: mint (required), verbose. Returns: ok, raw, cache, error, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Tools are mostly distinct: honeypot_check and rugcheck_report clearly separate EVM vs Solana safety checks; dex_search, dex_token_pairs, and dex_pair cover different granularities of pair data. Minor overlap exists between dex_search and dex_token_pairs, but descriptions clarify when each is appropriate.
All tool names use consistent snake_case and follow a predictable pattern: domain-specific prefix (dex_, jupiter_, honeypot_, rugcheck_) plus a clear noun or verb. The naming scheme makes the tool's function obvious and uniform across the set.
Six tools is a well-scoped size for a token research and safety-checking server. Each tool covers a distinct aspect of the workflow (search, pair lookup, pair snapshot, safety verification, pricing) without redundancy or bloat.
The core workflow (find token, verify pair, assess safety, get price) is covered. Minor gaps exist: no EVM-specific price source analogous to jupiter_prices, and dex_token_pairs only queries one chain at a time, requiring multiple calls for cross-chain analysis.
Maintenance
Related MCP Connectors
Read-only Solana token safety checks: risk score, honeypot, liquidity lock, authorities, holders.
Read-only honeypot, holder and liquidity scam checks for tokens across 64 networks.
Pre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.
Pay-per-call Solana token risk intelligence: 8 tools via x402. From $0.005 USDC, no API key.
Related MCP Servers
AlicenseAqualityBmaintenanceProvides post-deploy Solana threat intelligence, enabling AI agents to check operators, tokens, and network stats for detecting rug pulls and malicious activity.544 npm2MIT- AlicenseAqualityBmaintenanceCheck a token address before acting on a pool alert. VetAgent reports liquidity across eight chains. On Ethereum, BSC and Base, it reports available sell-simulation and tax evidence and whether the simulation matches the displayed pool. On Solana it checks token authorities and liquidity. An unavailable sell check is disclosed. Try one address over MCP or HTTP without an API key.3MIT
- AlicenseNot gradedqualityCmaintenanceRead-only token intelligence for Robinhood Chain and Solana, providing safety checks, ticker resolution, deployer records, whale wallet tracking, and outcome measurements via a hosted MCP server.MIT

GORZ MCP serverofficial
AlicenseNot gradedqualityCmaintenanceEnables AI assistants and trading agents to run Solana memecoin safety checks, including grades, red flags, launch bundles, same-second sellers, rug-farm links, and wallet activity.78 npmMIT