MCP.Market

web3ctx MCP server

online · 100% uptime
by FarseenSh·io.github.FarseenSh/web3ctx·v1.0.0

Version-true web3 docs, ABIs and human-validated integration recipes over MCP.

A87/100grade A
What users say
No reviews yet
Be the first
Safety scan
A87/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed web3ctx yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

web3ctx tools (5)

write = sends, deletes, buys or posts
  • web3_depsFree

    Dependency closure around a selector. Does not follow calls across projects.

  • web3_fetchFree

    Full bodies for selectors you already chose, or the next page of a cursor. Does not discover selectors.

  • web3_grepFree

    Exact lexical match on a known identifier. Does not rank semantically.

  • web3_lookupFree

    Typed records by id: address, ABI, EIP. Does not search prose or rank.

  • web3_searchFree

    Ranked selectors for a prose query or unknown identifier. Does not return bodies.

Public scan report

scanner v0.1.10 · 2026-10-29 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 980ms20/20
  • Tool poisoning5 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 38 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 87/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How web3ctx compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
87/100
higher than 70% of 1,301 Productivity servers
Tools
5
the typical Productivity server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote Productivity server answers 100%
Response time
361 ms
faster than 45% of 656 Productivity servers

What its tools let an agent do: 5 read

Install web3ctx in Claude Code, Cursor or VS Code

claude mcp add --transport http web3ctx https://mcp.scarai.xyz/mcp
Add to Cursor

What the publisher says

From the web3ctx repository's README, as published. We do not edit it. Read it on GitHub

web3ctx

The last mile before your agent signs.

Human-validated, chain-run web3 integration recipes, served version-true over MCP.

Five tools

A real answer

“how do I bridge USDC with CCTP” — one call to the authless endpoint, 2026-08-28:

{
  "intent": "lookup",
  "recipe": {
    "project_id": "cctp",
    "version": "2",
    "recipe_type": "usdc-bridge-send",
    "last_validated": "2026-08-07",
    "validated_by": "farseen (github: FarseenSh)",
    "receipts": {
      "validated_on": "2026-08-07",
      "validated_by": "farseen (github: FarseenSh)",
      "checks": [
        "attest",
        "test"
      ],
      "chains_exercised": [
        "base-sepolia",
        "arbitrum-sepolia"
      ],
      "on_chain": [
        {
          "kind": "txHash",
          "hash": "0xd4b4e6395f52ad726dd6062e7a7ec47a2d3a7875d36f20fbb154cde756a3d0f5",
          "role": "approve",
  // … 207 more lines — the receipts, the
  // validated recipe body, and ten citations each pinned to a commit or an exact package version.

The whole response is 26,191 bytes (sha256 bc58a9feba1f6309…) and it publishes byte-for-byte: evidence/showcase/cctp-search.json. Diff it against your own call.

Why this exists

It does not get fooled by a wrong premise. Ten questions built on premises verified false before the run — an archived repo, a renamed package, a version that does not exist. web3ctx was deceived 0 of 10; every other arm was deceived at least once (1–3 of 10). 🔴 Our own intent=integrate row was deceived once, and it publishes here beside the other: a stray line in one recipe cited an archived repository. The ten traps and every arm’s answer →

Citations you can re-fetch. Every unit carries project@version and a URL pinned to a 40-character commit: 142 of 144 across the audited payloads, against ~0 for every tool compared. The audit protocol →

When it does not know, it says so. Asked about eight projects it does not index, it declines all eight and names what would resolve each one. Competitors answer most of them. ⚠ Zero confabulated rows anywhere, including ours — that column separates nobody, and it is reported rather than claimed as an advantage. Abstention honesty →

The recipes are the moat. Each one was run by a human against live chains and ships with the transaction receipts, so anyone can check the claim by RPC rather than trusting the stamp.

Freshness, stated honestly

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

web3ctx: common questions

Is web3ctx MCP server safe?
Yes, by our scan: it is graded A (87/100). Read the web3ctx safety report
How do I install web3ctx?
It runs remotely at mcp.scarai.xyz. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does web3ctx need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is web3ctx maintained?
The last commit was 45 days ago (2026-09-21). The latest release is v1.0.0.
Is web3ctx up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of web3ctx?
Servers from other publishers that do the same job: SvGrid MCP server, no_human MCP server and loci MCP server.
How does web3ctx compare with other Productivity MCP servers?
safety score 87/100 (higher than 70% of 1,301 Productivity servers); tools 5 (the typical Productivity server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to web3ctx

Same job from other publishers: the closest match first, then the best rated.

  • SvGrid
    Checks AI-written SvGrid code against the real API, plus version-pinned Svelte 5 grid docs.
    A
  • no_human
    File a task with your local no_human and check on it: task_add and task_status over stdio.
    B
  • loci
    Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
    A
  • AI Context
    Local-first MCP server: version-correct library docs, code map, and offline drift for your repo.
    B
  • Context7
    Up-to-date docs for AI agents
    A