Xahau MCP

A Model Context Protocol server for the Xahau network with two firsts: it runs a Hook's real WebAssembly bytecode in a local VM (no xahaud node required), and it runs a Hooks-specific static-analysis / security rule engine over it - both fully offline. Around that core it adds read-only ledger access, a Xahau-aware binary codec, an instruction-count fee estimate, network-reward math, governance helpers, and…. Its 40 documented tools cover hook, decode, amendment, simulate.

People who need these tools inside Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-21 · ★ 6 · #690 OF 848 MAINTAINED OTHER · VERIFIED 2026-08-25

MIT · TypeScript servers · how we verify → /methodology

01 · Install Xahau MCP

before you install - you'll need

Set MAX_INFLIGHT, XAHC_HOOK_MEM_MB before connecting.

Claude Desktop

Settings → Extensions → Install, then select the https://github.com/Hugegreencandle/xahau-mcp/releases/download/v2.0.1/xahau-mcp-2.0.1.mcpb .mcpb bundle

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as Claude Desktop extension (.mcpb bundle)

license MIT - declared in the repository

registry namespace io.github.Hugegreencandle is GitHub-verified and matches the repo owner

03 · What Xahau MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can compare two hook versions - API/HookOn/size deltas + newly-gained sensitive capabilities, generate a starter Hook in C for an intent (firewall/payment-limit/state-counter/…) - then verify with analyze/execute, run the static-analysis rule engine over a hook → SARIF-lite findings, and diff enabled-amendment sets across two networks (e.g. mainnet vs testnet) - explains why a tx/Hook feature works on one but not the other.

Capability map

Tools grouped from the project's README - what Xahau MCP lets an agent do.

Hook

14 tools - e.g. Run the real Hook bytecode in a local VM against a simulated tx/state → actual accept/rollback, return code, state writes, emits, trace (LOCAL_VM).; Differential fuzzing: sweep many generated…

execute_hook · fuzz_hook · annotate_hook_trace · hook_report · hook_execution_postmortem · classify_hook…

Decode

7 tools - e.g. A SetHook tx → its hook definitions, HookOn decoded.; Decode an Import/Burn2Mint XPOP → source ledger, inner burn tx, burned drops, UNL validators.; Engine result code ⇄ name (e.g. 153 ⇄ tecHOOK_REJECTED).

decode_sethook · decode_xpop · decode_result · decode_amount · decode_sign_request · decode_lease_uri…

Simulate

1 tool - e.g. PRE-SIGN FLIGHT SIMULATOR - predict an unsigned tx's fate: originator + stakeholder hook chains (order canonical from xahaud Transactor.cpp/applyHook.cpp) run a

simulate_transaction

What

1 tool - e.g. TIME MACHINE - fetch a real historical tx, apply your overrides, re-simulate at its original ledger. Reproduces the real reward claim's GenesisMint to the drop

what_if

Fidelity

1 tool - e.g. Honest fidelity metric: replays a committed corpus of real mainnet HookExecutions through the VM and reports agreement % over comparable (non-degraded) runs onl

vm_fidelity_report

Audit

1 tool - e.g. Pull every hook on an account and analyze all of them.

audit_account_hooks

Diagnose

1 tool - e.g. "Why did my transaction fail?" - plain-English diagnosis from on-chain facts: engine result → cause + concrete fix (~30-code catalog), hook rollback return-stri

diagnose_failed_tx

Evernode

1 tool - e.g. One-call Evernode host health check (the official troubleshooting checklist, automated): registration entry, heartbeat liveness vs the on-chain active rule, ins

evernode_host_diagnostics

Latest releases

v2.0.1 · 2026-06-11

v2.0.1 - Hardening & honesty · A correctness/security patch on top of v2.0.0, from a full audit of the codebase. No new tools (still 61), no API surface changes beyond one small input rename (below). Tests 249 → 261…

v2.0.0 · 2026-06-11

simulate_transaction - the pre-sign flight simulator · Paste an unsigned transaction. Every hook it would trigger runs as real bytecode against real ledger state in the local VM - the one measured at 100% agreement on…

v1.9.0 · 2026-06-11

Watch Xahau governance live - seats, votes, tallies, thresholds · governance_state now decodes the entire Genesis Governance Game hook state (layout canonical from xahaud hook/genesis/govern.c): · All 20 seats and…

04 · Who maintains Xahau MCP

Xahau MCP is maintained by hugegreencandle. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

category
other - ranked #690 of 848 actively-maintained other servers as of 2026-08-25.
release cadence
10+ releases in the last 90 days (latest 2026-06-11)
registry
io.github.Hugegreencandle/xahau-mcp (active, first published 2026-06-10 · 7 versions)
packages
mcpb:https://github.com/Hugegreencandle/xahau-mcp/releases/download/v2.0.1/xahau-mcp-2.0.1.mcpb

06 · Xahau MCP FAQ

Is Xahau MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-21 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

What can Xahau MCP do?

With this server connected, an agent can compare two hook versions - API/HookOn/size deltas + newly-gained sensitive capabilities, generate a starter Hook in C for an intent (firewall/payment-limit/state-counter/…) - then verify with analyze/execute, run the static-analysis rule engine over a hook → SARIF-lite findings, and diff enabled-amendment sets across two networks (e.g. mainnet vs testnet) - explains why a tx/Hook feature works on one but not the other.

07 · Alternatives to Xahau MCP

More MCP servers to compare · Hustcc MCP Mermaid · Hydrolix · HYPD AI - Paid Ads & Analytics · Gaff Check · Tidal MCP

More TypeScript MCP servers · Code Cartographer · Agentic MCP · Human Pages · Project Human · see all