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.

Bouncer

PYPI · BOUNCER-MCP

Stdio MCP proxy that denies agent sends to destinations first seen in untrusted tool output.

Available components

0 this week 83 Trust /100

Last scanned (13 hours ago)

Scores higher than 83% 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
  • 1 of 30 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to Ezed9/mcp-bouncer). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 9 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability81
  • 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
  • Tool/resource definitions use about 322 tokens (~53/item across 6 items; 4 tools + 2 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 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

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • 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.

  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

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.

  • 21 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 20 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +1
    • Security disclosure: unverified → pass ▲ functional
  • 18 Nov 26 +14
    • Malware scan: unverified → pass ▲ security
    • Security disclosure: pass → unverified ▼ functional
  • 17 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 12 Nov 26 68

    First indexed and scored.

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/bouncer-mcp@0.1.6

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 Ezed9/mcp-bouncer
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Ezed9/mcp-bouncer/.github/workflows/release.yml@refs/tags/v0.1.6
Rekor log index 3828733903
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:63c7e36012b736fdaab70c7210cf0379e8e432cb6cec15ee50e802f75c9f8555

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 30 packages
Packages resolved 30
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~282 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
bouncer_audit_summary ~53

Retrieve recent audit log entries from Bouncer showing allowed, denied, and asked tool calls with their timestamps and reasons.

NameTypeReqDescription
limitinteger–Maximum number of recent entries to return (default: 20).

No output schema declared.

No examples provided.

bouncer_check_verdict ~121

Evaluate a hypothetical tool call against Bouncer's deterministic security contracts and return the verdict (ALLOW, DENY, or ASK) with the underlying reason, without executing the tool.

NameTypeReqDescription
argsobject–Arguments passed to the tool call.
toolstringyesName of the tool being called (e.g. 'send_email', 'write_file').
untrusted_contextarray–List of untrusted strings currently in context (from prior tool outputs).
user_policy_yamlstring–Optional YAML policy with custom contract overrides.

No output schema declared.

No examples provided.

bouncer_get_active_policies ~62

Inspect all active contract packs (builtin rules for filesystem, gmail, slack, github, gdrive) and user overrides loaded by Bouncer.

NameTypeReqDescription
pack_namestring–Optional name of a specific pack to inspect (e.g. 'filesystem').

No output schema declared.

No examples provided.

bouncer_verify_policy ~46

Validate a YAML policy string against Bouncer's schema and report syntax validity, contract rules count, and covered tools.

NameTypeReqDescription
policy_yamlstringyesYAML content defining tool policies.

No output schema declared.

No examples provided.

Install

How do I install the Bouncer MCP server?

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

pypi · bouncer-mcp

# add to Claude Code
claude mcp add ezed9-mcp-bouncer -- uvx bouncer-mcp serve
Common questions

What is the Bouncer MCP server?

Bouncer is an MCP server listed in the public MCP registry as io.github.Ezed9/mcp-bouncer. Stdio MCP proxy that denies agent sends to destinations first seen in untrusted tool output. This page covers its PyPI package (bouncer-mcp).

Is the Bouncer MCP server safe to use?

Bouncer scores 83 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 Bouncer MCP server expose?

Bouncer exposes 4 tools: bouncer_check_verdict, bouncer_verify_policy, bouncer_get_active_policies, bouncer_audit_summary. Their descriptions and schemas cost roughly 282 tokens of context every time the server is loaded.

Is the Bouncer MCP server still maintained?

Bouncer 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 Bouncer MCP server under?

Bouncer 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 Bouncer MCP server?

VerifyMCP ran 15 checks on Bouncer, 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 Bouncer: Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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.