AgentAvow Trust
REMOTE · AGENTAVOW.COM · 2 COMPONENTS
Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to
Available components
Last scanned (6 hours ago)
Scores higher than 96% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability80
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1414 tokens (~141/item across 10 items; 8 tools + 2 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 94% of tool parameters carry a description.Partial
- Structured output schemas are declared (38% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
- Supports UI / widget rendering.Pass
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.
- 29 Oct 26 0
- Resource “AgentAvow trust card” now points somewhere else: ui://agentavow/trust-card-v13.html → ui://agentavow/trust-card-v14.html security
- New resource “AgentAvow trust card (previous version)” functional
- 20 Oct 26 0
- MCP protocol: Implements a current MCP spec version (2026-07-28). functional
- MCP protocol version: 2025-11-25 → 2026-07-28 functional
- 18 Oct 26 0
- Stability: 0.97 → pass security
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 80. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Oct 26 +1
- Schema quality: 130 → 154 ▼ functional
- First check of Tool coverage: 38 functional
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 5 Nov 2026 · Probed https://agentavow.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=agentavow.com | CN=YE1,O=Let's Encrypt,C=US | 4 Nov 2026 | 2 Feb 2027 | ECDSA 256 | ECDSA-SHA384 | 6689df7f3d2069abde5c756aaefd133a584 |
| SANs: agentavow.com, www.agentavow.com | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of agentavow.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| agentavow.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; script-src 'self' https://cdn.jsdelivr.net https://accounts.google.com https://static.cloudflareinsights.com; style-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net https://accounts.google.com; img-src 'self' data: blob: https:; font-src 'self' https://cdn.jsdelivr.net; connect-src 'self' wss://agentavow.com https://accounts.google.com https://cloudflareinsights.com; frame-src https://accounts.google.com; frame-ancestors 'none'; form-action 'self'; base-uri 'self' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | geolocation=(), camera=(), microphone=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agentavow.com/mcp | Verified | 200 | |
| http (plaintext) | http://agentavow.com/mcp | HTTPS enforced | 301 | https://agentavow.com/mcp |
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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
about_agentavow About AgentAvow ~49
What AgentAvow is, which tool to use for what, how to read a verdict, and example scans. Call this for an overview or when getting started. No input, read-only.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
check_interaction_safety Check interaction safety ~101
Check whether it is safe to interact with another agent by trust threshold. Thresholds: delegate 0.6, trade 0.5, collaborate 0.4, follow 0.1. Returns is_safe, risk_level, the score, and a recommendation. Read-only, no auth.
| Name | Type | Req | Description |
|---|---|---|---|
| interaction_type | string | yes | – |
| target_entity_id | string | yes | UUID of a registered target entity (resolve one with lookup_identity). |
No output schema declared.
No examples provided.
get_trust_badge Get a trust badge ~75
Get an embeddable AgentAvow trust badge (SVG) for an entity, with ready-to-paste Markdown and HTML. The badge auto-updates as the score changes. Read-only, no auth.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_id | string | yes | UUID of a registered AgentAvow entity (resolve one with lookup_identity). |
No output schema declared.
No examples provided.
lookup_identity Look up an agent or tool ~71
Look up an AgentAvow entity by W3C DID or display name. Returns the entity's id, name, type, trust score and tier. Read-only, no auth. Use to resolve an identity before checking its trust.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | A did:web:... or a display name. |
No output schema declared.
No examples provided.
scan_mcp_server Scan an MCP server ~133
Scan a live MCP server's tool definitions for tool-poisoning, prompt-injection, invisible-unicode, and manifest-execution risks before your agent connects to it. Returns one of three answers with its reason (Safe to connect, Review before you connect, or Do not connect), a 0-100 trust score, findings, and a signed attestation. Read-only; calls the agentavow.com public API.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_url | string | yes | The MCP server's https:// URL. |
| force | boolean | – | Re-scan now instead of returning the cached verdict (results cache ~1h). |
| Name | Type | Req | Description |
|---|---|---|---|
| adoption | object|null | – | The adoption score: real usage (downloads per week, stars or installs). Never changes the decision. |
| advisories_affecting_version | array | – | Published advisories that affect this version. |
| cached | boolean | – | Served from the ~1h cache. |
| certified | boolean | – | Matches the signed attestation's certified.eligible. |
| certified_mark | boolean | – | Certified and safe: show the Certified mark. |
| coverage_gaps | object | – | Machine form of not_checked: gap kinds (e.g. tool_list_paged, oversized_files) with a flag or count. Empty when nothing was skipped. |
| critical | integer | – | Critical findings, static and sandbox. |
| decision | string | yes | The answer to lead with: safe = Safe to connect, review = Review before you connect, do_not_connect = Do not connect. |
| decision_final | boolean | yes | False while the behavioral sandbox is still running; the decision can still change. |
| decision_reason | string | yes | One sentence naming what decided it. |
| deprecated | string|null | – | The maintainer's deprecation notice, or null. |
| findings_total | integer | – | All findings, every severity. |
| high | integer | – | High findings, static and sandbox. |
| incident | object|null | – | Known past compromise (context only, never scored). |
| install | string|null | – | Install command, only when nothing blocks it. |
| not_checked | array | – | Plain-English notes for what the scan could not read or check (empty when it read everything). Say these alongside the answer. |
| package_version | string|null | – | Package version scanned. |
| published_at | string|null | – | When that version was published. |
| report_json_url | string | – | The full verdict as JSON. |
| report_url | string | yes | Full report page. |
| rescan_pending | boolean | – | A fresh scan was started; this is the previous result. |
| sandbox | object|null | – | What the behavioral sandbox observed; null if it does not apply. |
| scanned_at | string|null | – | When the scan ran (ISO 8601, UTC). |
| signed | boolean | – | True when a signed (Ed25519/JWS) attestation backs this. |
| static_findings_total | integer | – | Findings from static analysis only. |
| subscores | object | – | Per-category 0-100 scores behind the trust score. |
| target | string | yes | What was scanned, as given. |
| target_type | string | yes | github, npm, pypi, crates, docker, hf, or mcp. |
| tier | string|null | – | Trust tier for the score (detail, not the headline). |
| top_findings | array | – | Up to five most important findings. |
| trust_score | integer | yes | Trust score, 0-100. Evidence under the decision. |
| verdict | string | yes | Binary form of the decision, kept for older clients. |
| verdict_reason | string | – | Machine reason for the binary verdict, e.g. clean, clean_partial (clean, but not everything was read), blocking_findings, thin_coverage. |
| verify_url | string | – | How to verify offline. |
No examples provided.
scan_package Scan a package ~309
Scan a published package (npm, PyPI, crates, Docker, or Hugging Face) with AgentAvow. Returns one of three answers with its reason (Safe to connect, Review before you connect, or Do not connect), a 0-100 trust score, an adoption score from real usage (downloads per week), findings with remediation, and a signed attestation. Also reports published advisories that affect the scanned version, the maintainer's deprecation notice, repo-vs-artifact drift (files shipped that aren't in the source), and AgentAvow's behavioral sandbox results when available. Scans the latest version unless `version` (or a pin in the name) names one. Read-only; calls agentavow.com.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | – | Alias for registry. |
| force | boolean | – | Re-scan now instead of returning the cached verdict (results cache ~1h). Use after a new version ships. |
| name | string | yes | Package name, e.g. 'chalk' (or 'org/model' for hf). |
| registry | string | – | Package registry: npm, pypi, crates, docker, or hf. |
| surface | string | – | Alias for registry. |
| version | string | – | Exact version to scan, e.g. '5.3.0'. Optional: the latest version by default. A pin in the name ('chalk@5.3.0', 'requests==2.32.5') works too. |
| Name | Type | Req | Description |
|---|---|---|---|
| adoption | object|null | – | The adoption score: real usage (downloads per week, stars or installs). Never changes the decision. |
| advisories_affecting_version | array | – | Published advisories that affect this version. |
| cached | boolean | – | Served from the ~1h cache. |
| certified | boolean | – | Matches the signed attestation's certified.eligible. |
| certified_mark | boolean | – | Certified and safe: show the Certified mark. |
| coverage_gaps | object | – | Machine form of not_checked: gap kinds (e.g. tool_list_paged, oversized_files) with a flag or count. Empty when nothing was skipped. |
| critical | integer | – | Critical findings, static and sandbox. |
| decision | string | yes | The answer to lead with: safe = Safe to connect, review = Review before you connect, do_not_connect = Do not connect. |
| decision_final | boolean | yes | False while the behavioral sandbox is still running; the decision can still change. |
| decision_reason | string | yes | One sentence naming what decided it. |
| deprecated | string|null | – | The maintainer's deprecation notice, or null. |
| findings_total | integer | – | All findings, every severity. |
| high | integer | – | High findings, static and sandbox. |
| incident | object|null | – | Known past compromise (context only, never scored). |
| install | string|null | – | Install command, only when nothing blocks it. |
| not_checked | array | – | Plain-English notes for what the scan could not read or check (empty when it read everything). Say these alongside the answer. |
| package_version | string|null | – | Package version scanned. |
| published_at | string|null | – | When that version was published. |
| report_json_url | string | – | The full verdict as JSON. |
| report_url | string | yes | Full report page. |
| rescan_pending | boolean | – | A fresh scan was started; this is the previous result. |
| sandbox | object|null | – | What the behavioral sandbox observed; null if it does not apply. |
| scanned_at | string|null | – | When the scan ran (ISO 8601, UTC). |
| signed | boolean | – | True when a signed (Ed25519/JWS) attestation backs this. |
| static_findings_total | integer | – | Findings from static analysis only. |
| subscores | object | – | Per-category 0-100 scores behind the trust score. |
| target | string | yes | What was scanned, as given. |
| target_type | string | yes | github, npm, pypi, crates, docker, hf, or mcp. |
| tier | string|null | – | Trust tier for the score (detail, not the headline). |
| top_findings | array | – | Up to five most important findings. |
| trust_score | integer | yes | Trust score, 0-100. Evidence under the decision. |
| verdict | string | yes | Binary form of the decision, kept for older clients. |
| verdict_reason | string | – | Machine reason for the binary verdict, e.g. clean, clean_partial (clean, but not everything was read), blocking_findings, thin_coverage. |
| verify_url | string | – | How to verify offline. |
No examples provided.
scan_repo Scan a GitHub repo ~196
Scan a public GitHub repository with AgentAvow and return whether it is safe for an agent to connect to: one of three answers with its reason (Safe to connect, Review before you connect, or Do not connect), a 0-100 trust score, an adoption score from real usage (stars), the findings behind it (with where and how to fix), and a signed, offline-verifiable attestation. Read-only, no account. Calls the AgentAvow public API at agentavow.com.
| Name | Type | Req | Description |
|---|---|---|---|
| force | boolean | – | Re-scan now instead of returning the cached verdict (results cache ~1h). Use after the target has changed. |
| owner | string | – | Repo owner (optional if 'repo' is already 'owner/name'). |
| repo | string | yes | Repo as 'owner/name' (e.g. 'vercel/next.js'), or just the name when 'owner' is given separately. |
| Name | Type | Req | Description |
|---|---|---|---|
| adoption | object|null | – | The adoption score: real usage (downloads per week, stars or installs). Never changes the decision. |
| advisories_affecting_version | array | – | Published advisories that affect this version. |
| cached | boolean | – | Served from the ~1h cache. |
| certified | boolean | – | Matches the signed attestation's certified.eligible. |
| certified_mark | boolean | – | Certified and safe: show the Certified mark. |
| coverage_gaps | object | – | Machine form of not_checked: gap kinds (e.g. tool_list_paged, oversized_files) with a flag or count. Empty when nothing was skipped. |
| critical | integer | – | Critical findings, static and sandbox. |
| decision | string | yes | The answer to lead with: safe = Safe to connect, review = Review before you connect, do_not_connect = Do not connect. |
| decision_final | boolean | yes | False while the behavioral sandbox is still running; the decision can still change. |
| decision_reason | string | yes | One sentence naming what decided it. |
| deprecated | string|null | – | The maintainer's deprecation notice, or null. |
| findings_total | integer | – | All findings, every severity. |
| high | integer | – | High findings, static and sandbox. |
| incident | object|null | – | Known past compromise (context only, never scored). |
| install | string|null | – | Install command, only when nothing blocks it. |
| not_checked | array | – | Plain-English notes for what the scan could not read or check (empty when it read everything). Say these alongside the answer. |
| package_version | string|null | – | Package version scanned. |
| published_at | string|null | – | When that version was published. |
| report_json_url | string | – | The full verdict as JSON. |
| report_url | string | yes | Full report page. |
| rescan_pending | boolean | – | A fresh scan was started; this is the previous result. |
| sandbox | object|null | – | What the behavioral sandbox observed; null if it does not apply. |
| scanned_at | string|null | – | When the scan ran (ISO 8601, UTC). |
| signed | boolean | – | True when a signed (Ed25519/JWS) attestation backs this. |
| static_findings_total | integer | – | Findings from static analysis only. |
| subscores | object | – | Per-category 0-100 scores behind the trust score. |
| target | string | yes | What was scanned, as given. |
| target_type | string | yes | github, npm, pypi, crates, docker, hf, or mcp. |
| tier | string|null | – | Trust tier for the score (detail, not the headline). |
| top_findings | array | – | Up to five most important findings. |
| trust_score | integer | yes | Trust score, 0-100. Evidence under the decision. |
| verdict | string | yes | Binary form of the decision, kept for older clients. |
| verdict_reason | string | – | Machine reason for the binary verdict, e.g. clean, clean_partial (clean, but not everything was read), blocking_findings, thin_coverage. |
| verify_url | string | – | How to verify offline. |
No examples provided.
verify_trust Verify an entity's trust score ~108
Verify an AgentAvow entity's trust score. Returns trust_score (0-1), trust_score_pct (0-100), trust_tier, and whether it meets a minimum threshold. Read-only, no auth. Use before interacting with an unknown agent.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_id | string | yes | UUID of a registered AgentAvow entity (resolve one with lookup_identity; unknown ids return guidance, not an error). |
| min_trust | number | – | Min score, 0-1. |
No output schema declared.
No examples provided.
How do I install the AgentAvow Trust MCP server?
AgentAvow Trust is a hosted endpoint at https://agentavow.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · agentavow.com
claude mcp add --transport http com-agentavow-agentavow-trust 'https://agentavow.com/mcp'
What is the AgentAvow Trust MCP server?
AgentAvow Trust is an MCP server listed in the public MCP registry as com.agentavow/agentavow-trust. Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to. This page covers its hosted endpoint (https://agentavow.com/mcp).
Is the AgentAvow Trust MCP server safe to use?
AgentAvow Trust scores 88 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the AgentAvow Trust MCP server expose?
AgentAvow Trust exposes 8 tools: scan_repo, scan_package, scan_mcp_server, verify_trust, check_interaction_safety, and 3 more. Their descriptions and schemas cost roughly 1,042 tokens of context every time the server is loaded.
Does the AgentAvow Trust MCP server require authentication?
No. We connected to AgentAvow Trust without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the AgentAvow Trust MCP server still maintained?
AgentAvow Trust is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.