Agentmetry vs DepScope: Which is Better in 2026?
A comprehensive comparison of Agentmetry and DepScope covering features, pricing, use cases, and which tool is the right choice for your needs.
⚡ Quick Verdict
Choose Agentmetry if:
- →You want more affordable paid plans (from $2/mo)
- →You need records agent activity at the tool boundary or mitre att&ck technique tagging per event
Choose DepScope if:
- →You need a broader feature set (8 features vs 6)
- →You need hallucination guard verifies packages against live registries in 19 ecosystems or typosquat detection by levenshtein distance to popular package names
ChatGPT already recommends Agentmetry or DepScope. Does it recommend yours?
If you're building an AI tool, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.
Agentmetry vs DepScope: At a Glance
Pricing Comparison: Agentmetry vs DepScope
Understanding the pricing differences between Agentmetry and DepScope is crucial for making the right choice. Here's how their plans compare side by side.
Agentmetry Pricing
💡 Pricing takeaway: Both Agentmetry and DepScope offer free tiers, making it easy to try before you buy. Compare the specific plans to find the best value for your use case.
Feature-by-Feature Comparison
Here's how every feature from Agentmetry and DepScope stacks up.
What Makes Each Tool Unique
🔵 Unique to Agentmetry
Features available in Agentmetry but not in DepScope:
- ✓Records agent activity at the tool boundary
- ✓MITRE ATT&CK technique tagging per event
- ✓Sequence correlation into single critical alerts
- ✓Runs fully local with zero cloud calls
- ✓Secret values excluded from the trail
- ✓SIEM-readable output format
🟣 Unique to DepScope
Features available in DepScope but not in Agentmetry:
- ✓Hallucination guard verifies packages against live registries in 19 ecosystems
- ✓Typosquat detection by Levenshtein distance to popular package names
- ✓Live CVE intel from OSV, CISA KEV, EPSS, and the OpenSSF malicious feed
- ✓Severity, fix version, and migration path returned in one call
- ✓~300-token briefs replacing 4–8k tokens of scraping per decision (−74%)
- ✓8.5M packages, 19 ecosystems, 22 MCP tools
- ✓Remote MCP with zero install in Claude Desktop, Cursor, and Windsurf
- ✓Browser manifest scan plus a published 10-model hallucination benchmark
Use Case Recommendations
Best for: Agentmetry
Agentmetry is a local flight recorder for AI coding agents, written for the security engineer who found out their company was running Cursor by reading a pull request. Endpoint detection sees a process; it does not see that an agent read a private SSH key and then made an outbound network call in the same session. Agentmetry records agent activity at the tool boundary — every read, shell command and fetch — correlates the sequence, tags it against MITRE ATT&CK technique IDs, and raises a single critical alert for the pattern rather than a stream of individually unremarkable events. The worked example on the homepage is exactly that: a `cat ~/.ssh/id_rsa` read tagged T1552.004, an `aws configure list` shell call tagged T1059 with DLP flagging an AWS access key, and a WebFetch to a paste site tagged T1071.001, correlated into one credential-exfil finding. Secret values themselves are never written to the trail. It runs entirely on the machine with zero cloud calls, ships nine detection rules in the current phase, and emits in a format existing SIEMs already read, so it slots into an established pipeline rather than becoming another console. Install is a git clone plus `pip install -e`, with a PowerShell installer for Windows. The whole thing is Apache-2.0 open source with the code public, which matters for a tool whose entire value proposition is that it watches privileged activity.
Ideal use cases:
- •Teams or individuals who need records agent activity at the tool boundary
- •Teams or individuals who need mitre att&ck technique tagging per event
- •Teams or individuals who need sequence correlation into single critical alerts
- •Teams or individuals who need runs fully local with zero cloud calls
- •Anyone focused on security workflows
- •Anyone focused on agents workflows
Best for: DepScope
DepScope is a free MCP server that screens every package an AI agent suggests before it reaches npm install. It targets three specific failure modes. The first is hallucination: LLMs invent plausible-sounding package names, and DepScope verifies each one against live registries across 19 ecosystems and flags typosquats by Levenshtein distance to popular packages — the exact mechanism attackers rely on when they register a name a model is likely to hallucinate. The second is vulnerability exposure, covered by live lookups against OSV, CISA's Known Exploited Vulnerabilities list, EPSS scores, the OpenSSF malicious-package feed, and a deprecated-package index, returning severity, fix version, and migration path in one call. The third is token cost: pre-curated briefs of roughly 300 tokens replace the four-to-eight thousand tokens an agent would otherwise burn scraping registry and CVE pages per decision, a reported 74% reduction. It covers 8.5 million packages across 19 ecosystems — npm, PyPI, Cargo, Go, Composer, Maven, NuGet, RubyGems, pub, hex, Swift, CPAN, Hackage, CRAN, conda, Homebrew, JSR, and Julia — with 22 MCP tools, no auth, no API key, and no rate limit. Remote MCP works out of the box in Claude Desktop, Cursor, and Windsurf, with a curl one-liner for everything else, and the SDKs are open source. There is also a browser paste-a-manifest scan and a published ten-model hallucination benchmark.
Ideal use cases:
- •Teams or individuals who need hallucination guard verifies packages against live registries in 19 ecosystems
- •Teams or individuals who need typosquat detection by levenshtein distance to popular package names
- •Teams or individuals who need live cve intel from osv, cisa kev, epss, and the openssf malicious feed
- •Teams or individuals who need severity, fix version, and migration path returned in one call
- •Anyone focused on mcp workflows
- •Anyone focused on supply-chain workflows
🛡️ Other AI Security & Testing Tools to Consider
Agentmetry and DepScope aren't the only options. Here are other popular tools in the same space:
Lineation
Security control plane for AI agents — zero-trust agent identity, LLM and MCP gateways, policy-as-code, and prompt-injection defense
Axtary
Payload-bound authorization for AI agents — human approval is cryptographically tied to the exact action, so a changed payload is denied
Tracecat
Open-source SOAR for AI-native security teams — agents, cases, and workflows with human approval gates
Trestle
Local secret scanner with an MCP server so coding agents check their own output
ZeroLeaks
Continuous AI red teaming for agents, endpoints and MCP tools, with unlimited scans on every plan
Bot Butcher
LLM-based spam classification API for contact forms — a reCAPTCHA alternative with no visitor friction
Is one of these your tool?
This page ranks for "Agentmetry vs DepScope" — buyers comparing the two land here, and ChatGPT and Perplexity cite it. Claim your listing for $19 one-time — no subscription, nothing to cancel — and get a Featured badge, top placement in your category, and a permanent dofollow backlink. Prefer it ongoing? Monthly is one click away on the next page.
Frequently Asked Questions
Is Agentmetry better than DepScope?
It depends on your needs. Agentmetry offers 6 key features including Records agent activity at the tool boundary and MITRE ATT&CK technique tagging per event, while DepScope provides 8 features including Hallucination guard verifies packages against live registries in 19 ecosystems and Typosquat detection by Levenshtein distance to popular package names. Agentmetry uses a open-source model with a free tier, while DepScope is free with free access available. Choose based on which features and pricing model align with your requirements.
Is Agentmetry cheaper than DepScope?
DepScope doesn't have standard paid plans, while Agentmetry starts at Apache-2.0 open source, installed from GitHub. No paid tier or pricing page is published as of August 2026.. Both tools offer free tiers, so you can try each before committing. Always check the official websites for the most current pricing.
Can I use Agentmetry and DepScope together?
Yes, many users combine Agentmetry and DepScope in their workflow. Agentmetry excels at records agent activity at the tool boundary, while DepScope shines with hallucination guard verifies packages against live registries in 19 ecosystems. Using both allows you to leverage the strengths of each tool, though this means managing two subscriptions — though free tiers can help manage costs.
What's the main difference between Agentmetry and DepScope?
While both are ai security & testing tools, Agentmetry emphasizes records agent activity at the tool boundary, whereas DepScope is known for hallucination guard verifies packages against live registries in 19 ecosystems. The best choice depends on your specific workflow and feature priorities.
Learn More
📬 Get the best new AI tools delivered weekly
One concise email with fresh launches, trending picks, and featured standouts.