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

SelfHeal MCP

NPM · SELFHEAL-MCP · SCANNED AUG 3

Self-healing proxy for MCP servers with retry, circuit breaker, and observability

Available components

+18 this week 64 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability71
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 419 tokens (~83/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · selfheal-mcp

# add to Claude Code
claude mcp add carsonroell-debug-selfheal-mcp -- npx -y selfheal-mcp
# add to Codex CLI
codex mcp add carsonroell-debug-selfheal-mcp -- npx -y selfheal-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "carsonroell-debug-selfheal-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "selfheal-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add carsonroell-debug-selfheal-mcp --command npx --arg -y --arg selfheal-mcp
# ~/.hermes/config.yaml
mcp_servers:
  carsonroell-debug-selfheal-mcp:
    command: "npx"
    args: ["-y", "selfheal-mcp"]
// mcp.json
{
  "mcpServers": {
    "carsonroell-debug-selfheal-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "selfheal-mcp"
      ]
    }
  }
}
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.

  • 2 Aug 26 +43
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Tool coverage: 100 → unverified functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Schema quality: unverified → good functional
    • Licence: MIT functional
  • 31 Jul 26 −25
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 +22
    • Tool coverage: unverified → 100 functional
  • 28 Jul 26 −22
    • Tool coverage: 100 → unverified functional
    • First check of Schema quality: unverified functional
  • 27 Jul 26 46

    First indexed and scored.

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 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 5 exposed · ~315 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.

Tool Tokens
circuit_reset ~41

Reset a circuit breaker back to closed (healthy). Use after fixing the underlying issue.

NameTypeReqDescription
targetstringTarget to reset. Omit to reset all.

No output schema declared.

No examples provided.

circuit_status ~43

Check the health status of a target. Returns circuit state, failure count, and cooldown.

NameTypeReqDescription
targetstringTarget to check. Omit to see all targets.

No output schema declared.

No examples provided.

metrics ~43

Get observability metrics — success rates, latency, top errors, breakdown by tool and target.

NameTypeReqDescription
windowMinutesnumberTime window in minutes (default: 60)

No output schema declared.

No examples provided.

recent_errors ~39

Get the most recent failed calls with full error details and retry logs.

NameTypeReqDescription
limitnumberNumber of errors to return (default: 20)

No output schema declared.

No examples provided.

wrap_call ~149

Execute a function call with retry, circuit breaker, and metrics. Pass a target name and the function will be retried on transient failures. Use this to wrap any unreliable external call.

NameTypeReqDescription
bodystringRequest body (for POST/PUT/PATCH)
descriptionstringyesHuman-readable description of what this call does
headersobjectHTTP headers
methodstringHTTP method (default: GET)
targetstringyesIdentifier for the target service (used for circuit breaker tracking)
timeoutMsnumberTimeout per attempt in ms (default: 30000)
urlstringURL to call (for HTTP targets)

No output schema declared.

No examples provided.