Update to AgentAvow
Snapshot Nov 19, 2026 · 01:02 UTC · version 1.1.3
Product listing or positioning changed
Long description — Now says: It works in ChatGPT and in Codex: in Codex, ask about a server or package before you run codex mcp add or install it.
Observed in the public listing; claims come from the publisher.
Up to 3 plugins free · no card required.
All fields and original values.
Long description
Oct 27, 2026 · 01:01 UTC
Nov 19, 2026 · 01:02 UTC
It works in ChatGPT and in Codex: in Codex, ask about a server or package before you run codex mcp add or install it.
Declared skills
Oct 27, 2026 · 01:01 UTC
[{"description":"Check whether an MCP server, a published package, or a GitHub repo is safe to connect to or install. AgentAvow answers Safe to connect, Review before you connect, or Do not connect, with the reason, a signed 0-100 trust ...
Nov 19, 2026 · 01:02 UTC
[{"description":"Check whether an MCP server, a published package, or a GitHub repo is safe to connect to or install. AgentAvow answers Safe to connect, Review before you connect, or Do not connect, with the reason, a signed 0-100 trust ...
Composer icon url
Oct 27, 2026 · 01:01 UTC
https://files.openai.com/content?id=file_00000000a2d481f5a9bd7da849e53dc2
Nov 19, 2026 · 01:02 UTC
https://files.openai.com/content?id=file_0000000008748212b7e0b01804609450
Logo url
Oct 27, 2026 · 01:01 UTC
https://files.openai.com/content?id=file_00000000422081f596bfd4decf6ac8c2
Nov 19, 2026 · 01:02 UTC
https://files.openai.com/content?id=file_00000000fb608212ab7b3a8a9ad316a9
Compare saved observations
Download comparison JSONFull technical diff · 6 changed fields
changed /release/id
"pluginrel_31ac7500c9e8819199c76b0c173d140c"
"pluginrel_a934833eaf488191a7315e46f2842e4c"
changed /release/interface/composer_icon_url
"https://files.openai.com/content?id=file_00000000a2d481f5a9bd7da849e53dc2"
"https://files.openai.com/content?id=file_0000000008748212b7e0b01804609450"
changed /release/interface/logo_url
"https://files.openai.com/content?id=file_00000000422081f596bfd4decf6ac8c2"
"https://files.openai.com/content?id=file_00000000fb608212ab7b3a8a9ad316a9"
changed /release/interface/long_description
"AgentAvow tells you whether a tool is safe before your agent connects to it. Give it an MCP server, a package from npm, PyPI, crates or Docker, or a GitHub repo, and it answers in plain words: Safe to connect, Review before you connect, or Do not connect, with the reason. Underneath are two scores: a 0–100 trust score, backed by a signed attestation anyone can recompute offline, and an adoption score built from real usage (downloads, stars, installs). It checks for known-malicious versions, published advisories, supply-chain and dependency risk, and code-safety issues, can run the tool in a sandbox to see what it actually does, and shows an interactive trust card. Eight read-only tools cover scanning a repo, package, or live MCP server; verifying a score; checking interaction safety before you connect; looking up an identity; and getting an embeddable badge. No account, no sign-in, and nothing is modified — every call is anonymous and read-only."
"AgentAvow tells you whether a tool is safe before your agent connects to it. Give it an MCP server, a package from npm, PyPI, crates or Docker, or a GitHub repo, and it answers in plain words: Safe to connect, Review before you connect, or Do not connect, with the reason. It works in ChatGPT and in Codex: in Codex, ask about a server or package before you run codex mcp add or install it. Underneath are two scores: a 0–100 trust score, backed by a signed attestation anyone can recompute offline, and an adoption score built from real usage (downloads, stars, installs). It checks for known-malicious versions, published advisories, supply-chain and dependency risk, and code-safety issues, can run the tool in a sandbox to see what it actually does, and shows an interactive trust card. Eight read-only tools cover scanning a repo, package, or live MCP server; verifying a score; checking interaction safety before you connect; looking up an identity; and getting an embeddable badge. No account, no sign-in, and nothing is modified — every call is anonymous and read-only."
changed /release/skills
[
{
"description": "Check whether an MCP server, a published package, or a GitHub repo is safe to connect to or install. AgentAvow answers Safe to connect, Review before you connect, or Do not connect, with the reason, a signed 0-100 trust score and an adoption score. Use when the user asks whether a specific tool, package, repo, or MCP server is safe or trustworthy, or asks to vet one before installing or connecting it.",
"interface": {
"brand_color": null,
"default_prompt": "Is the npm package chalk safe to install?",
"display_name": "Scan before connect",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Check a tool's safety before you connect or install it"
},
"name": "scan-before-connect",
"plugin_release_skill_id": "pluginrsk_6ac830ce54e4819181b1a0bb52660689"
}
][
{
"description": "Check whether an MCP server, a published package, or a GitHub repo is safe to connect to or install. AgentAvow answers Safe to connect, Review before you connect, or Do not connect, with the reason, a signed 0-100 trust score and an adoption score. Use when the user asks whether a specific tool, package, repo, or MCP server is safe or trustworthy, or asks to vet one before installing or connecting it.",
"interface": {
"brand_color": null,
"default_prompt": "Is the npm package chalk safe to install?",
"display_name": "Scan before connect",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Check a tool's safety before you connect or install it"
},
"name": "scan-before-connect",
"plugin_release_skill_id": "pluginrsk_6afdecde544c8191ab0e09adc3ff8687"
}
]changed /release/version
"1.1.2"
"1.1.3"
Full snapshot data
{
"canonical_app_id": "asdk_app_6ac830ccc2d48191ac27974dec7d8344",
"connector_id": "asdk_app_6ac830ccc2d48191ac27974dec7d8344",
"created_at": "2026-10-09T01:28:24.915047Z",
"discoverability": "LISTED",
"id": "plugin_asdk_app_6ac830ccc2d48191ac27974dec7d8344",
"is_template": false,
"is_template_instance": false,
"is_v2_template": false,
"name": "agentavow",
"release": {
"app_ids": [
"asdk_app_6ac830ccc2d48191ac27974dec7d8344"
],
"app_manifest": {
"apps": {
"agentavow": {
"id": "asdk_app_6ac830ccc2d48191ac27974dec7d8344",
"required": true
}
}
},
"app_templates": [],
"description": "Scan an MCP server, package, or GitHub repo for a signed 0-100 trust score before your agent connects to it.",
"display_name": "AgentAvow",
"id": "pluginrel_a934833eaf488191a7315e46f2842e4c",
"interface": {
"brand_color": null,
"capabilities": [
"Interactive",
"Read"
],
"category": "Developer Tools",
"composer_icon_dark_url": null,
"composer_icon_url": "https://files.openai.com/content?id=file_0000000008748212b7e0b01804609450",
"default_prompt": "Is the npm package chalk safe to install?",
"default_prompts": [
"Is the npm package chalk safe to install?",
"Should I connect the MCP server at https://agentavow.com/mcp?",
"Check the GitHub repo modelcontextprotocol/servers before I use it"
],
"developer_name": "Kenne Ives",
"logo_url": "https://files.openai.com/content?id=file_00000000fb608212ab7b3a8a9ad316a9",
"logo_url_dark": null,
"long_description": "AgentAvow tells you whether a tool is safe before your agent connects to it. Give it an MCP server, a package from npm, PyPI, crates or Docker, or a GitHub repo, and it answers in plain words: Safe to connect, Review before you connect, or Do not connect, with the reason. It works in ChatGPT and in Codex: in Codex, ask about a server or package before you run codex mcp add or install it. Underneath are two scores: a 0–100 trust score, backed by a signed attestation anyone can recompute offline, and an adoption score built from real usage (downloads, stars, installs). It checks for known-malicious versions, published advisories, supply-chain and dependency risk, and code-safety issues, can run the tool in a sandbox to see what it actually does, and shows an interactive trust card. Eight read-only tools cover scanning a repo, package, or live MCP server; verifying a score; checking interaction safety before you connect; looking up an identity; and getting an embeddable badge. No account, no sign-in, and nothing is modified — every call is anonymous and read-only.",
"plugin_category_id": "developer tools",
"privacy_policy_url": "https://agentavow.com/legal/privacy",
"screenshot_urls": [],
"short_description": "Is this tool safe to connect?",
"terms_of_service_url": "https://agentavow.com/legal/terms",
"website_url": "https://agentavow.com"
},
"keywords": [
"security",
"trust",
"mcp",
"supply-chain",
"code-scanning",
"attestation"
],
"mcp_servers": [
{
"key": "agentavow",
"metadata": {
"headers": {},
"type": "streamable-http",
"url": "https://agentavow.com/mcp"
}
}
],
"onboarding_skill_name": null,
"requires_local_executor": false,
"skills": [
{
"description": "Check whether an MCP server, a published package, or a GitHub repo is safe to connect to or install. AgentAvow answers Safe to connect, Review before you connect, or Do not connect, with the reason, a signed 0-100 trust score and an adoption score. Use when the user asks whether a specific tool, package, repo, or MCP server is safe or trustworthy, or asks to vet one before installing or connecting it.",
"interface": {
"brand_color": null,
"default_prompt": "Is the npm package chalk safe to install?",
"display_name": "Scan before connect",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Check a tool's safety before you connect or install it"
},
"name": "scan-before-connect",
"plugin_release_skill_id": "pluginrsk_6afdecde544c8191ab0e09adc3ff8687"
}
],
"version": "1.1.3"
},
"scope": "GLOBAL",
"share_url": "https://chatgpt.com/plugins/plugin_asdk_app_6ac830ccc2d48191ac27974dec7d8344?open_in_app",
"status": "ENABLED"
}SHA-256 of public snapshot: c83eaf53688586c17f9a8edace10d0f0f804846bcd9a40c1c4019a6a7b504236