BLACK_WALL MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Blackwall irreversible-action risk forecasts: Do risk classes remain advisory predictions rather than claims that a tool enforces the agent's final action?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Pre-action risk assessment for irreversible/high-stakes agent actions.

What we know

Single-tool risk gate that evaluates a proposed action/payload/context and returns risk score, reversibility, named red flags and an advisory gate/recommendation before execution.

Maintenance / activity evidence

blackwall-mcp 1.4.3 published 2026-08-28T16:24:55.109Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: medium.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Advisory/gating analysis only; no direct target-system mutation.
API key.
Sensitive access: Potential PII/secrets inside action payloads, High-stakes operation context

Safety advisory is valuable but only enforceable if the orchestrator honors the gate.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do risk classes remain advisory predictions rather than claims that a tool enforces the agent's final action?

The bounded review of the publisher's documented Blackwall irreversible-action risk forecasts and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Safety advisory is valuable but only enforceable if the orchestrator honors the gate.
Advisory/gating analysis only; no direct target-system mutation.
API key.
Proposed action payloads may include SQL, recipients, amounts, paths or message text and are sent for risk analysis.
Sensitive access: Potential PII/secrets inside action payloads, High-stakes operation context
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
first-party package/repository evidence
retention/privacy of submitted action payloads
The MCP evaluates and returns a verdict; it does not technically prevent a caller from ignoring the result unless the surrounding workflow enforces it.
Third-party source used for detailed tool schema because first-party package page was not available in this pass.
Latency/cost depend on provider plan.

Original activity observations

blackwall-mcp 1.4.3 published 2026-08-28T16:24:55.109Z

Technical identity

npm/blackwall-mcp

Exact implementation source: https://www.npmjs.com/package/blackwall-mcp ↗
Reviewed resource type: MCP Server
Package identity: npm:blackwall-mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
blackwall-mcp
Recorded package identity, distribution or download evidence.
Evidence source ↗
blackwalltier.com
Source material retained for this review.
Includes references whose attribution is not established.
Directory reference ↗
mcp.so/servers/blackwall-mcp
Source material retained for this review.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Warning

Not runtime tested, no third-party installation, network authorization, paid calls, or mutation executed.
Do not claim production service is available based on README alone.
Publisher observe mode available for no-write testing; gate forecast does not automatically stop other tools
Official npm publisher package page README inspected for this exact npm identity; static research only. Some setup statements are conservatively summarized; no source code or live client execution checked. V2 review did not run any live client.
Check actual host syntax and supply credentials in secure client environment; do not paste placeholders verbatim.
Avoid write, payment, token transfer, publishing, sending, booking and remote account changes as tests.
Replace credential, action and registration placeholders; follow the matching publisher/client prerequisites. No execution performed.
Use the matching host, actual registration name and original installation environment; this does not revoke credentials.

Install / connect
Publisher instructions
Publisher observe mode available for no-write testing; gate forecast does not automatically stop other tools | Publisher npm README revisited on 2026-10-14; exact identity retained.
Reviewed setup example · Claude Code only · Publisher instructions · Review before use
```
claude mcp add blackwall -e BLACKWALL_API_KEY=<KEY> -- npx -y blackwall-mcp
```
Configure / authenticate
MCP100 setup guide
BLACKWALL_API_KEY required. Use non-blocking observe mode only if intentionally configured; do not test with destructive actions.
Required environment variables: BLACKWALL_API_KEY
Check connection
Suggested check
Check client tools or publisher status, do not invoke risky action.
Remove / uninstall / revoke
MCP100 setup guide
If registered by the publisher Claude Code example under `blackwall`, run the provided unregister command; for a different MCP client or name, delete the actual client registration. Removing a local client entry is distinct from deleting a vendor account/token.
Remove named client registration · Claude Code only · MCP100 composed guide
claude mcp remove blackwall

Official Documentation & Sources

What it does

Single-tool risk gate that evaluates a proposed action/payload/context and returns risk score, reversibility, named red flags and an advisory gate/recommendation before execution.

Capability: Security & Testing
Resource type: MCP Server
Best fit: Pre-action risk assessment for irreversible/high-stakes agent actions.

Representative uses

Assess payments before send
Flag dangerous SQL/delete operations
Detect prompt-injection/PII/context mismatches
Require human confirmation for high-risk actions

Limitations

The MCP evaluates and returns a verdict; it does not technically prevent a caller from ignoring the result unless the surrounding workflow enforces it.
Third-party source used for detailed tool schema because first-party package page was not available in this pass.
Latency/cost depend on provider plan.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: API key.
Permissions: Advisory/gating analysis only; no direct target-system mutation.
Data handling: Proposed action payloads may include SQL, recipients, amounts, paths or message text and are sent for risk analysis.
Cost: freemium
Risk and cautions: Safety advisory is valuable but only enforceable if the orchestrator honors the gate.

Access scope and cautions

Write actions: None in the reviewed inventory
Sensitive access: Potential PII/secrets inside action payloads High-stakes operation context
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Assess payments before send; Flag dangerous SQL/delete operations; Detect prompt-injection/PII/context mismatches; Require human confirmation for high-risk actions.

What authentication is documented?

BLACK_WALL API key.

Can it modify data or perform write operations?

The reviewed inventory lists no write actions. An empty inventory alone does not establish read-only authority. Recorded permission boundary: Advisory/gating analysis only; no direct target-system mutation.

What data-handling boundary should I consider?

Proposed action payloads may include SQL, recipients, amounts, paths or message text and are sent for risk analysis. Recorded sensitive-access context: Potential PII/secrets inside action payloads; High-stakes operation context.

What limitations and risks should I check before use?

Safety advisory is valuable but only enforceable if the orchestrator honors the gate. The MCP evaluates and returns a verdict; it does not technically prevent a caller from ignoring the result unless the surrounding workflow enforces it. Third-party source used for detailed tool schema because first-party package page was not available in this pass. Latency/cost depend on provider plan. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.