Agents

Name: Agents
Author: obsmetrics

@obsmetricsMCP server · External

Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.

AI agent governancev0.0.8

Freeno charge per call

One address for any MCP client. No sign-in needed on this server.

Safety · AI6%Low risk
Does · AIReads1 read · 1 act, by tool name
ConnectRemote · no sign-inStreamable HTTP
PopularityNo stars yetUpdated 16 Jun 2026
StatusAll clearAnswered Odel on 12 Oct

What it does

1 read1 act5 other

Grouped by tool name. At most: only reads or looks up information.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Tools

7 · grouped by tool name · checked 12 Oct 2026

Read · 1Look things up

secret-scan

Act · 1Change something

sign-guard

Other · 5Neither hinted nor named

secure-code-review
pr-summary
x402-trust-audit
inject-guard
tool-call-guard

Try it in the Inspector

No README yet. What Odel knows about this module is on the right.

Similar modules

Browse AI agent governance

MCP server: One MCP server.
Claude Flow
@ruvnet · External73,814 GitHub stars.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Agent-Native Dispatch
@builderio · External7,121 GitHub stars.
Central Slack/Telegram router with jobs, memory, approvals, and A2A delegation
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
OuroborosRun by its publisher: served from their own domain, namespace checked by the registry.
@q00 · External6,192 GitHub stars.
Pins an acceptance spec; the verify command and expected output never enter the success contract.
10% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
10% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
10% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
OmnaraRun by its publisher: served from their own domain, namespace checked by the registry.
@omnara · External2,905 GitHub stars.
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Tradememory ProtocolRun by its publisher: served from their own domain, namespace checked by the registry.
@mnemox-ai · External1,427 GitHub stars.
Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Bernstein
@chernistry · External1,416 GitHub stars.
Declarative agent orchestration for engineering teams
4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Deprecated by the publisher: Superseded by io.github.sipyourdrink-ltd/bernstein after the repository moved to the organisation account.Free to use.
4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Deprecated by the publisher: Superseded by io.github.sipyourdrink-ltd/bernstein after the repository moved to the organisation account.Free to use.
4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Deprecated by the publisher: Superseded by io.github.sipyourdrink-ltd/bernstein after the repository moved to the organisation account.Free to use.
MCP server: One MCP server.
BernsteinRun by its publisher: served from their own domain, namespace checked by the registry.
@sipyourdrink-ltd · External1,215 GitHub stars.
The open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.
7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
AttestixRun by its publisher: served from their own domain, namespace checked by the registry.
@vibetensor · External874 GitHub stars.
AI agent identity, W3C credentials, EU AI Act compliance. 47 MCP tools.
7% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.