io.github.egoughnour/code-firewall-mcp
PYPI · CODE-FIREWALL-MCP · 2 COMPONENTS
Structural similarity-based code filter. Stops malicious code pattern reaching execution tools.
Available components
Last scanned (22 hours ago)
Scores higher than 80% 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 Security75
- No malware found by supply-chain analysis.Pass
- A critical CVE affects chromadb, and no fixed version has been published yet. View diagnostics → Fail
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 8 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency95
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to egoughnour/code-firewall-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 289 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability75
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 686 tokens (~62/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management63
- Stability observed for 19 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
- Structured output schemas are declared (100% of tools); any adoption earns full credit.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; "firewall_remove_pattern" implies "remove" 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 11 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
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.
- 4 Nov 26 +9
- Malware scan: unverified → pass ▲ security
- Stability: pass → 0.63 functional
- 30 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 29 Oct 26 +1
- Stability: 0.97 → pass security
- 28 Oct 26 +14
- Malware scan: unverified → pass ▲ security
- Stability: pass → 0.97 functional
- 26 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 24 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 23 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 22 Oct 26 +4
- Known CVEs: unverified → fail ▼ security
- Stability: 0.97 → pass security
- Dependency health: unverified → 0.97 ▲ 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 4 Nov 2026 · Analysed pypi/code-firewall-mcp@0.7.0
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 | egoughnour/code-firewall-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/egoughnour/code-firewall-mcp/.github/workflows/release.yml@refs/tags/v0.7.0 |
| Rekor log index | 834258991 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:3b3b972c279107167a964ca0490eac2c0c74ff567a36078ea76038c2ab98dde1 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Vulnerabilities 8 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-2wm9-hf6c-p5cr | CVE-2026-45830 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
| GHSA-36p7-vc44-83pf | CVE-2026-45833 | critical | no | |
| GHSA-f4j7-r4q5-qw2c | CVE-2026-45829 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H | no |
| GHSA-xph7-9rjv-w5fr | CVE-2026-45831 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
| PYSEC-2026-311 | CVE-2026-45829 | none | no | |
| PYSEC-2026-3813 | CVE-2026-45830 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
| PYSEC-2026-3814 | CVE-2026-45833 | none | no | |
| PYSEC-2026-3815 | CVE-2026-45831 | high | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H | no |
Background: What a vulnerability scan can and cannot prove →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 7 |
| No linked repository | 1 |
| 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 →
firewall_blacklist Firewall Blacklist ~93
Add a code pattern to the blacklist. Either file_path or code must be provided.
| Name | Type | Req | Description |
|---|---|---|---|
| code | – | – | Code string to blacklist (alternative to file_path) |
| file_path | – | – | Path to code file to blacklist |
| language | string | – | Programming language (used if code is provided) |
| reason | string | – | Why this pattern is dangerous |
| severity | string | – | critical, high, medium, low |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_check Firewall Check ~63
Check if code is safe to pass to execution tools like rlm_exec. Parses the code, normalizes to structural skeleton, embeds via Ollama, and checks similarity against blacklisted dangerous patterns.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Path to the code file to check |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_check_code Firewall Check Code ~45
Check if code string is safe (without requiring a file).
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The code to check |
| language | string | – | Programming language (default: python) |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_list_patterns Firewall List Patterns ~47
List patterns in the blacklist or delta collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collection_name | string | – | "blacklist" or "deltas" |
| limit | integer | – | Maximum number of patterns to return |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_ollama_status Firewall Ollama Status ~34
Check Ollama server status and embedding model availability.
| Name | Type | Req | Description |
|---|---|---|---|
| force_refresh | boolean | – | Force refresh the cached status |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_record_delta Firewall Record Delta ~112
Record a near-miss variant to help sharpen the classifier. Use this when code is similar to a blacklisted pattern but represents a legitimate use case, or when a new variant of a dangerous pattern is discovered.
| Name | Type | Req | Description |
|---|---|---|---|
| code | – | – | Code string (alternative to file_path) |
| file_path | – | – | Path to code file |
| language | string | – | Programming language |
| notes | string | – | Notes about why this is being recorded |
| similar_to | string | – | Pattern ID this is similar to |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_remove_pattern Firewall Remove Pattern ~48
Remove a pattern from the blacklist or delta collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collection_name | string | – | "blacklist" or "deltas" |
| pattern_id | string | yes | The pattern ID to remove |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_setup_ollama Firewall Setup Ollama ~85
Install Ollama via Homebrew (macOS).
| Name | Type | Req | Description |
|---|---|---|---|
| install | boolean | – | Install Ollama via Homebrew |
| model | string | – | Model to pull (default: nomic-embed-text) |
| pull_model | boolean | – | Pull the embedding model (nomic-embed-text) |
| start_service | boolean | – | Start Ollama as a background service |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_setup_ollama_direct Firewall Setup Ollama Direct ~95
Install Ollama via direct download (macOS) - no Homebrew, no sudo.
| Name | Type | Req | Description |
|---|---|---|---|
| install | boolean | – | Download and install Ollama to ~/Applications |
| model | string | – | Model to pull (default: nomic-embed-text) |
| pull_model | boolean | – | Pull the embedding model (nomic-embed-text) |
| start_service | boolean | – | Start Ollama server in background |
Structured output declared, but exposes no named fields.
No examples provided.
firewall_status Firewall Status ~14
Get firewall status and statistics.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
firewall_system_check Firewall System Check ~50
Check if system meets requirements for Ollama embeddings. Verifies: macOS, Apple Silicon (M1/M2/M3/M4), RAM, Homebrew installed. Use before attempting Ollama setup.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the io.github.egoughnour/code-firewall-mcp server?
io.github.egoughnour/code-firewall-mcp runs locally as a PyPI package, launched with uvx code-firewall-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 · code-firewall-mcp
claude mcp add egoughnour-code-firewall-mcp -- uvx code-firewall-mcp
What is the io.github.egoughnour/code-firewall-mcp server?
io.github.egoughnour/code-firewall-mcp is listed in the public MCP registry as io.github.egoughnour/code-firewall-mcp. Structural similarity-based code filter. Stops malicious code pattern reaching execution tools. This page covers its PyPI package (code-firewall-mcp).
Is the io.github.egoughnour/code-firewall-mcp server safe to use?
io.github.egoughnour/code-firewall-mcp scores 80 out of 100 on VerifyMCP. We recorded 8 known advisories against it as of 4 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 io.github.egoughnour/code-firewall-mcp server expose?
io.github.egoughnour/code-firewall-mcp exposes 11 tools: firewall_system_check, firewall_setup_ollama, firewall_setup_ollama_direct, firewall_ollama_status, firewall_check, and 6 more. Their descriptions and schemas cost roughly 686 tokens of context every time the server is loaded.
Is the io.github.egoughnour/code-firewall-mcp server still maintained?
io.github.egoughnour/code-firewall-mcp is still listed as active in the MCP registry. We last reached this channel on 4 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 io.github.egoughnour/code-firewall-mcp server under?
io.github.egoughnour/code-firewall-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.