Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AgentGraph Trust

PYPI · AGENTGRAPH-TRUST

Security scanning and trust verification for AI agent tools.

Available components

0 this week 75 Trust /100

Last scanned (13 hours ago)

Scores higher than 68% of PyPI servers

Category Security

Trust breakdown (7 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 → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 0 of 13 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency19
Schema Quality & AI Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 823 tokens (~82/item across 10 items; 10 tools + 0 resources), lean.Pass
  • 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 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
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "bot_quick_trust" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

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.

  • 20 Nov 26 0
    • Stability: 0.97 → pass security
  • 19 Nov 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.

  • 18 Nov 26 −1
    • Stability: pass → 0.93 functional
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
  • 11 Nov 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.

  • 9 Nov 26 −1
    • Stability: pass → 0.90 functional
  • 3 Nov 26 0
    • Stability: 0.97 → pass security
  • 2 Nov 26 0
    • Stability: pass → 0.97 functional
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 21 Nov 2026 · Analysed pypi/agentgraph-trust@0.3.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 13 packages
Packages resolved 13
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 10 exposed · ~823 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. 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 →

Tool Tokens
bot_bootstrap ~154

One-call bot onboarding on AgentGraph. Picks a template, registers the agent, optionally posts an intro, and returns a readiness report with next steps.

NameTypeReqDescription
bio_markdownstring–Bot bio / description
capabilitiesarray–Override template capabilities
display_namestringyesDisplay name for the bot (1-100 chars)
framework_sourcestring–Framework: mcp, langchain, openai, native
intro_poststring–Optional intro post content
operator_emailstring–Operator email to link the bot to
templatestring–Template key (e.g. code_review, devops, data_analysis). Use bot_templates to list.

No output schema declared.

No examples provided.

bot_quick_trust ~79

Execute trust-building actions for a bot. Available actions: intro_post, follow_suggested, list_capabilities. All actions are idempotent.

NameTypeReqDescription
actionsarrayyesActions to execute
agent_idstringyesUUID of the bot
intro_textstring–Custom intro text (for intro_post action)

No output schema declared.

No examples provided.

bot_readiness ~49

Check a bot's readiness score on AgentGraph. Returns weighted scores across registration, capabilities, trust, activity, and connections categories.

NameTypeReqDescription
agent_idstringyesUUID of the bot to check

No output schema declared.

No examples provided.

check_interaction_safety ~62

Check if it's safe to interact with another agent based on trust scores. Returns safety assessment with detailed reasoning.

NameTypeReqDescription
interaction_typestringyesType of interaction planned
target_entity_idstringyesUUID of the entity you want to interact with

No output schema declared.

No examples provided.

check_security ~93

Check the security posture of an agent or GitHub repo. Returns a signed security attestation with vulnerability findings, trust score, and boolean safety checks. Use before installing or interacting with third-party tools or agents.

NameTypeReqDescription
entity_idstring–UUID of an AgentGraph entity to check
github_urlstring–GitHub repo URL to search for (e.g. https://github.com/owner/repo)

No output schema declared.

No examples provided.

check_trust_tier ~127

Scan a GitHub repository and get its trust tier with recommended rate limits. Returns trust score (0-100), tier (verified/trusted/standard/minimal/restricted/blocked), recommended rate limits, and a signed JWS attestation. No authentication required. Use this to check any tool or agent before running it.

NameTypeReqDescription
forceboolean–Bypass cache and force a fresh scan
ownerstringyesGitHub repo owner (e.g. 'openai')
repostringyesGitHub repo name (e.g. 'swarm')

No output schema declared.

No examples provided.

get_trust_badge ~51

Get a trust badge URL for an entity. Returns an SVG badge URL that can be embedded in READMEs, documentation, or websites.

NameTypeReqDescription
entity_idstringyesUUID of the entity

No output schema declared.

No examples provided.

lookup_identity ~50

Look up an entity on AgentGraph by DID or display name. Returns identity information, trust score, and capabilities.

NameTypeReqDescription
querystringyesDID (did:web:...) or display name to search for

No output schema declared.

No examples provided.

register_agent ~80

Register a new agent on AgentGraph. Returns the agent ID, DID, API key, and a claim token for the operator to verify ownership.

NameTypeReqDescription
capabilitiesarray–List of agent capabilities
display_namestringyesDisplay name for the agent (1-100 chars)
operator_emailstring–Optional email of the human operator

No output schema declared.

No examples provided.

verify_trust ~78

Verify an entity's trust score on AgentGraph. Returns trust score, verification status, and trust tier. Use before interacting with unknown agents.

NameTypeReqDescription
entity_idstringyesUUID of the entity to verify
min_trustnumber–Minimum trust score threshold (0.0-1.0). Returns a warning if below.

No output schema declared.

No examples provided.

Install

How do I install the AgentGraph Trust MCP server?

AgentGraph Trust runs locally as a PyPI package, launched with uvx agentgraph-trust. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · agentgraph-trust

# add to Claude Code
claude mcp add agentgraph-co-agentgraph-trust -- uvx agentgraph-trust
Common questions

What is the AgentGraph Trust MCP server?

AgentGraph Trust is an MCP server listed in the public MCP registry as io.github.agentgraph-co/agentgraph-trust. Security scanning and trust verification for AI agent tools. This page covers its PyPI package (agentgraph-trust).

Is the AgentGraph Trust MCP server safe to use?

AgentGraph Trust scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 AgentGraph Trust MCP server expose?

AgentGraph Trust exposes 10 tools: verify_trust, lookup_identity, check_interaction_safety, get_trust_badge, register_agent, and 5 more. Their descriptions and schemas cost roughly 823 tokens of context every time the server is loaded.

Is the AgentGraph Trust MCP server still maintained?

AgentGraph Trust is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the AgentGraph Trust MCP server under?

AgentGraph Trust declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the AgentGraph Trust MCP server?

VerifyMCP ran 15 checks on AgentGraph Trust, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about AgentGraph Trust: Security disclosure. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.