AgentStamp (vinaybhosle/agentstamp) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 37 tools. No publisher has claimed this listing.

Caution

56/100

AgentStamp

Item: AgentStamp
Rating: 56
Author: M8ven

Identity certification, public registry, reputation scoring, and x402 micropayments for AI agents built on Base and Solana.

→ vinaybhosle/agentstamp· npm: agentstamp-verify· 52 installs· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

vinaybhosle

Source: Glama · also listed on PulseMCP

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here PulseMCPnot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

⚠️

Known vulnerabilities in dependencies: 3 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 4 credentials: ADMIN_KEY, ANALYTICS_KEY, AUTH_SECRET, BLIND_TOKEN_SECRET

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes37 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

stamp_mint_bronze

Mint a bronze identity certificate (24h). $0.001 via x402 USDC.

stamp_mint_silver

Mint a silver identity certificate (7d). $0.005 via x402 USDC.

stamp_mint_gold

Mint a gold identity certificate (30d). $0.01 via x402 USDC.

stamp_verify

Verify an identity certificate by ID (free).

stamp_stats

Get stamp statistics (free).

registry_register

registry_search

Search the agent directory (free).

registry_browse

Browse all registered agents (free).

registry_endorse

Endorse an agent. $0.005 via x402 USDC.

registry_leaderboard

Top endorsed agents and category breakdown (free).

agent_reputation

Get agent reputation score (0-100) with full breakdown (free).

well_wish

Cast a wish for a capability. $0.001 via x402 USDC.

well_grant

Grant a wish. $0.005 via x402 USDC.

well_browse

Browse wishes (free).

well_trending

Trending wish categories (free).

well_stats

Wish statistics (free).

well_insights

Market insights: what AI agents want. $0.01 via x402 USDC.

get_passport

Get a signed cross-protocol agent passport. Contains identity, stamp, reputation, A2A card, and MCP metadata — all Ed25519-signed.

get_a2a_card

Get A2A agent card for Google A2A protocol (free).

trust_check

Single-call trust verdict for any wallet address. Returns whether the agent is trusted, their score, tier, and profile info. Unregistered agents get trusted: false with a registration CTA.

trust_compare

Compare trust scores of up to 5 wallets side-by-side. See who leads, the score gap, and which agents are unregistered.

trust_network

Network-wide trust statistics: total agents, stamps, endorsements, wishes, average reputation, top categories. Social proof for the AgentStamp network.

search_agents

Search the AgentStamp agent directory by query and/or category. Returns agents with reputation scores.

get_agent

Get full agent profile by ID, including endorsements and reputation score.

verify_stamp

Verify an AgentStamp identity certificate by its stamp ID.

browse_agents

Browse registered agents with optional category filter and sorting.

get_leaderboard

Get the agent leaderboard — top endorsed agents with reputation scores, newest agents, and category breakdown.

browse_wishes

Browse wishes from the Wishing Well. Discover what capabilities AI agents want.

get_trending

Get trending wish categories and velocity from the Wishing Well.

get_agent_reputation

Get an agent's reputation score (0-100) with full breakdown by tier, endorsements, uptime, age, and wishes granted.

bridge_erc8004_lookup

Look up an ERC-8004 on-chain agent and get their AgentStamp trust score. Free. Returns on-chain identity + trust verdict.

bridge_erc8004_trust_check

Get an AgentStamp trust verdict for an ERC-8004 agent. Free. Returns trusted/untrusted with score.

compliance_report

Get EU AI Act compliance report for an agent. Returns risk level, transparency declaration, audit summary, and trust status. Free.

get_verifiable_credential

Get a W3C Verifiable Credential for an agent. Returns the agent passport in W3C VC Data Model 2.0 format, interoperable with any VC verifier. Free.

dns_discovery

Check if a domain has an AgentStamp DNS TXT record for agent discovery. Verifies _agentstamp.domain.com TXT record and cross-checks with the registry. Free.

team_trust_check

Trust verdict for a multi-agent team. Returns aggregate trust score (0-100), weakest-link analysis, and per-member breakdown. Teams with score >= 10 and 2+ members are considered trusted.

create_team

Create a new agent team for multi-agent trust scoring. Owner is auto-added as first member. Note: for production use, prefer the REST API (POST /api/v1/teams) which requires wallet signature verification.

// known CVEs in dependencies3 high1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

highnanoid@3.3.11GHSA-28wg-ghj8-5hjv

nanoid: non-secure generators can loop indefinitely with negative size

highnanoid@3.3.11GHSA-2v37-7h3g-55p8

nanoid: custom generators can loop indefinitely when size is zero

highnanoid@3.3.11GHSA-xwg4-73v4-xw9w

nanoid: Integer Overflow or Wraparound

lowvitest@4.1.0GHSA-82fw-gwwq-j7x9

Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock

Depend on this server? Get alerted when its CVEs change.Watch this server free →

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

🔐 secretADMIN_KEY

🔐 secretANALYTICS_KEY

🔐 secretAUTH_SECRET

🔐 secretBLIND_TOKEN_SECRET

configCORS_ORIGIN

configDB_PATHSQLite database path

configERC8004_RPC_URL

configFACILITATOR_URLx402 facilitator

configHOST

configIP_HASH_SALT

configNETWORK

configRATE_LIMIT_ANALYTICS_MAX

configRATE_LIMIT_FREE_TIER_MAX

configRATE_LIMIT_FREE_TIER_WINDOW_MS

configRATE_LIMIT_MAX_REQUESTS

configRATE_LIMIT_MUTATION_MAX

configRATE_LIMIT_READ_MAX

configRATE_LIMIT_WINDOW_MS

configSANCTIONS_CHECK_ENABLED

configSIGNING_KEY_PATH

configSOLANA_WALLET_ADDRESSSolana wallet for USDC payments

configWALLET_ADDRESSEVM wallet for USDC payments on Base

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployPORT

deploySENTRY_DSN

deploySENTRY_DSN_AS

deploySENTRY_RELEASE

deploySENTRY_TRACES_RATE

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

37/37 tools missing one or more hints — stamp_mint_bronze (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); stamp_mint_silver (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); stamp_mint_gold (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +34 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 1/37 tools referenced in tests (3%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 3 high severity in production deps — nanoid@3.3.11 (high), nanoid@3.3.11 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dependency freshness

1/17 production deps stale: tweetnacl@2023-04-12 (3.4y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/vinaybhosle/agentstamp?variant=verified)](https://m8ven.ai/mcp/vinaybhosle/agentstamp)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 3010e90ba164f910bc2aff495078d82696cc9ce7

code hash: 70b5597b7aa955d49fe39eb7c26067efdb14ae471231a5ac4ce08f5b56b04909

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client