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.

io.github.EverMint-app/evermint-mcp

NPM · EVERMINT-MCP · SCANNED AUG 3

Mint tamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.

Available components

+19 this week 65 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 Security86
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (94 of 98), 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 (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability76
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 615 tokens (~123/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • 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 · evermint-mcp

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

  • 3 Aug 26 +24
    • Provenance: unverified → fail security
    • Known CVEs: unverified → partial security
    • Install scripts: unverified → pass security
    • Schema quality: unverified → excellent functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • Licence: MIT functional
  • 2 Aug 26 +20
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • MCP protocol: unverified → pass 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
  • 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 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

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

MCP tools — 5 exposed · ~615 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
evermint_get_record ~86

Fetch the full contents of a single EverMint record by Record ID, including the original payload that was minted. Requires authentication and the record must belong to the authenticated org. Use this when an agent needs to retrieve the actual content of a prior decision or action it recorded.

NameTypeReqDescription
record_idstringyesThe EverMint Record ID to fetch (format: EVR-XXXXXXXX)

No output schema declared.

No examples provided.

evermint_list_records ~159

List EverMint records belonging to the authenticated account. Supports filtering by agent_id, action_type, and date range. Returns record IDs, action types, timestamps, and agent IDs, not full payloads. Use this when an agent needs to audit its own past actions or build context from prior decisions.

NameTypeReqDescription
action_typestringFilter to a specific action type
agent_idstringFilter to records minted by a specific agent
limitnumberMax records to return (1-200, default 50)
sincestringISO 8601: only return records on or after this time
untilstringISO 8601: only return records on or before this time

No output schema declared.

No examples provided.

evermint_mint ~160

Mint a tamper-evident, cryptographically timestamped record of an AI agent action, decision, or observation. Returns a Record ID and SHA-256 hash that can be used to prove what the agent did and when. Use this whenever an agent takes an action that may need to be audited, disputed, or verified later.

NameTypeReqDescription
action_typestringyesShort label for the action being recorded (e.g. transaction_approved, decision_made, data_accessed)
agent_idstringIdentifier for this agent or system
payloadobjectThe state, decision, or context to preserve. Any JSON object.
timestampstringISO 8601 datetime or 'auto'. Defaults to auto.

No output schema declared.

No examples provided.

evermint_verify ~66

Verify an existing EverMint record by Record ID. Confirms the record exists, has not been altered, and returns its metadata. No API key required, verification is public.

NameTypeReqDescription
record_idstringyesThe EverMint Record ID to verify (format: EVR-XXXXXXXX)

No output schema declared.

No examples provided.

evermint_verify_chain ~144

Verify the integrity of a sequence of hash-chained EverMint records. Confirms each record's hash matches its content, and that each record correctly references the prior record in the chain with no gaps or tampering. Use this to prove an entire sequence of agent decisions is intact, not just a single record. This is public, no API key required.

NameTypeReqDescription
lengthnumberUsed with start_record_id. Max records to walk (1-100, default 10)
record_idsarrayOrdered list of Record IDs to verify as a chain, oldest first
start_record_idstringVerify the chain starting from this record forward

No output schema declared.

No examples provided.