Verfy
PYPI · VERFY
Ask before acting: would a command run, is an MCP config risky, what do the receipts say
Available components
Last scanned (13 hours ago)
Scores higher than 62% of PyPI servers
Category Security
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 Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to verfy-dev/verfy). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability70
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 402 tokens (~67/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (15)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- 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.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
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 →
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 +3
- Stability: unverified → 0.23 ▲ functional
- Package version: 0.23.1 → 0.26.3 functional
- Package version: 0.23.1 → 0.26.2 functional
- Package version: 0.23.1 → 0.26.1 functional
- 18 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 17 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 14 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Nov 26 66
First indexed and scored.
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/verfy@0.26.3
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | verfy-dev/verfy |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/verfy-dev/verfy/.github/workflows/publish.yml@refs/tags/cli-v0.26.3 |
| Rekor log index | 4027620076 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:5e08d4f5d9658dcc8a6314df9779f6208942576ba064ae72406dc8af30369c0d |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
agent_settings Risky agent settings ~36
List the settings of the coding agents on this computer that weaken them or switch Verfy off, with the fix for each. Reads only.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
check_line Check a shell command ~54
Say what Verfy's rules decide for a terminal line before an agent uses it: allow, ask or deny, and which rule decides. The line is only read.
| Name | Type | Req | Description |
|---|---|---|---|
| line | string | yes | The line, as written |
No output schema declared.
No examples provided.
check_tool_call Check a tool call ~75
Say whether Verfy's rules would allow, ask about or deny a call to a tool with these arguments. Nothing is called.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | – | The arguments of the call |
| server | string | – | The MCP server the tool belongs to, if any |
| tool | string | yes | The tool's name |
No output schema declared.
No examples provided.
recent_receipts Latest receipts ~50
Show the latest signed receipts of checked calls (time, verdict, tool and rules; arguments are not stored) and whether the chain verifies.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | How many (default 20) |
No output schema declared.
No examples provided.
scan_mcp_config Check an MCP config ~89
Check how the MCP servers in a config are started: packages without a version, a download piped into a shell, plain http, a key written into the file, a privileged container. Give the config's JSON text, or leave it out to check the configs found on this computer. No server is started.
| Name | Type | Req | Description |
|---|---|---|---|
| config | string | – | The JSON text of an MCP config (optional) |
No output schema declared.
No examples provided.
scan_tools Scan tool definitions ~62
Scan MCP tool definitions (a tools/list result) for warning signs such as hidden instructions and odd parameters. Returns a grade and the findings per tool.
| Name | Type | Req | Description |
|---|---|---|---|
| server | string | – | A name for the server (optional) |
| tools | array | yes | The tool definitions |
No output schema declared.
No examples provided.
How do I install the Verfy MCP server?
Verfy runs locally as a PyPI package, launched with uvx verfy mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · verfy
claude mcp add verfy-dev-verfy -- uvx verfy mcp
What is the Verfy MCP server?
Verfy is an MCP server listed in the public MCP registry as io.github.verfy-dev/verfy. Ask before acting: would a command run, is an MCP config risky, what do the receipts say. This page covers its PyPI package (verfy).
Is the Verfy MCP server safe to use?
Verfy scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 Verfy MCP server expose?
Verfy exposes 6 tools: check_line, check_tool_call, scan_mcp_config, scan_tools, agent_settings, recent_receipts. Their descriptions and schemas cost roughly 366 tokens of context every time the server is loaded.
Is the Verfy MCP server still maintained?
Verfy 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 Verfy MCP server under?
Verfy 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 Verfy MCP server?
VerifyMCP ran 15 checks on Verfy, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Verfy: Malware scan. 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.