Skip to main content
Glama
tokensift

tokensift

Official
by abetoots

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_check

honeypot.is buy/sell simulation

ethereum, bsc, base

rugcheck_report

rugcheck.xyz risk report

solana

dex_search

DexScreener search

all

dex_token_pairs

DexScreener pools for a token

ethereum, bsc, base, solana

dex_pair

DexScreener pair snapshot

ethereum, bsc, base, solana

jupiter_prices

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      # stdio

See 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 to TOKENSIFT_LIMITER_WAIT_S (5 s) and then returns rate_limited with retry_after_s. rate_limited and upstream_unavailable are never cached; invalid_input and not_found are cached for TOKENSIFT_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 become upstream_unavailable (403 advice names the datacenter-IP possibility).

  • raw is returned only with verbose=true, capped at TOKENSIFT_RAW_MAX_BYTES (32 kB) with raw_truncated=true when cut.

  • Logging goes to stderr only; stdout is the MCP wire.

  • Dual-era: the server answers both a legacy initialize handshake and modern 2026-07-28 per-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) accepts is_error with structured content, so errors are returned as results, never raised (a raised exception becomes a JSON-RPC error in mcp 2.x).

  • mcp.server.runner drives serve_dual_era_loop; a legacy initialize is handled inline and negotiated from HANDSHAKE_PROTOCOL_VERSIONS. tests/test_stdio.py proves both handshakes over a pipe.

  • The Envelope field ok forbids a classmethod of the same name; factories are Envelope.success / Envelope.failed.

  • MCP Inspector CLI v2 parses flags anywhere on its command line, so a target like uvx --from … tokensift-mcp loses --from and reports "Connection closed". scripts/serve-stdio.sh is a flag-free launcher for the Inspector; the three CLIs pass args through correctly and use uvx directly.

Available Tools

6 tools
dex_pairDexScreener pair snapshotA
Read-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_token_pairsDexScreener pools for a tokenA
Read-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)A
Read-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)A
Read-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)A
Read-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

    A4.2/5.0

    Scored across 6 tools

    Disambiguation4/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Provides post-deploy Solana threat intelligence, enabling AI agents to check operators, tokens, and network stats for detecting rug pulls and malicious activity.
      5
      44 npm
      2
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Check 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.
      3
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Read-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
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables 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 npm
      MIT