HiddenContent MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Hidden-content inspection before an agent reads documents: Do capability settings keep detection-only and sanitization behavior distinct for hidden document text?

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

Best fit

Preflight scanning of documents for hidden or deceptive content before an agent reads them.

What we know

Local stdio document-security MCP that checks PDF/Office/RTF/HTML-type content for hidden or deceptive payloads before downstream agent use.

Maintenance / activity evidence

@hiddencontent/mcp 0.4.15 published 2026-09-27T19:38:20.270Z

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

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Read/scan document scope.
HCS API token.
Sensitive access: Potentially sensitive documents, API token

Read-oriented security preflight; document sensitivity and service data handling are the main concerns.

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

All limitations / Review context

Do capability settings keep detection-only and sanitization behavior distinct for hidden document text?

The bounded review of the publisher's documented Hidden-content inspection before an agent reads documents 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.

Read-oriented security preflight; document sensitivity and service data handling are the main concerns.
Read/scan document scope.
HCS API token.
Local package processes documents; service-backed scanning may send detection requests according to product configuration.
Sensitive access: Potentially sensitive documents, API token
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.
Repository identity
Complete retention policy for service-backed scanning
Requires HCS_API_TOKEN according to package setup.
Hosted and local offerings have different data boundaries.
Full retention/security details are not all present on the npm page.

Original activity observations

@hiddencontent/mcp 0.4.15 published 2026-09-27T19:38:20.270Z

Technical identity

npm/@hiddencontent/mcp

Exact implementation source: https://www.npmjs.com/package/@hiddencontent/mcp ↗
Reviewed resource type: MCP Server
Package identity: npm:@hiddencontent/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 7, 2026

Package registry ↗
@hiddencontent/mcp
Recorded package identity, distribution or download evidence.
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.

Install / connect
Publisher instructions
HCS_API_TOKEN and HCS_CAPABILITIES=tool-use per publisher MCP configuration.
publisher install or stdio launch · Publisher instructions
npx -y @hiddencontent/mcp

Configure / authenticate

MCP100 setup guide

HCS_API_TOKEN and HCS_CAPABILITIES=tool-use per publisher MCP configuration.

claude desktop or cursor mcpServers json · MCP100 composed guide

{
  "mcpServers": {
    "hiddencontent": {
      "args": [
        "-y",
        "@hiddencontent/mcp"
      ],
      "command": "npx",
      "env": {
        "HCS_API_TOKEN": "YOUR_TOKEN",
        "HCS_CAPABILITIES": "tool-use"
      }
    }
  }
}

Check connection
Suggested check
After configuring HCS_API_TOKEN, inspect the check_document tool in the MCP host. Only submit a disposable non-sensitive fixture; this may transmit content to the provider.
Remove / uninstall / revoke
MCP100 setup guide
If you added this integration to Claude Code under the registration name `hiddencontent`, run `claude mcp remove hiddencontent` to unregister that client entry. In Claude Desktop, Cursor, VS Code or another host, delete/disable the corresponding named MCP registration in that host's settings and restart/reconnect. If you installed an npm package globally or operate a separate HTTP server, uninstall/stop it with its original deployment method. This does not delete user data or revoke service credentials.
MCP client unregister, stopping hosted processes, package uninstall, OAuth disconnect and token revocation are distinct actions.
A claude mcp remove command is only valid for Claude Code when the local registration actually has that name. Other MCP hosts require their own UI/config cleanup.
Separate provider credential revocation · publisher documented: HiddenContent official API reference: GET /v1/keys lists key IDs; POST /v1/keys/{keyId}/revoke revokes target key and every descendant key it minted. Requires an authorized bearer key. Revocation is consequential and must never be used as a connection test.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove hiddencontent

Official Documentation & Sources

What it does

Local stdio document-security MCP that checks PDF/Office/RTF/HTML-type content for hidden or deceptive payloads before downstream agent use.

Capability: Security & Testing
Resource type: MCP Server
Industry: Cybersecurity
Best fit: Preflight scanning of documents for hidden or deceptive content before an agent reads them.

Representative uses

Scan documents before ingestion
Detect hidden/deceptive content
Gate document-to-agent workflows

Limitations

Requires HCS_API_TOKEN according to package setup.
Hosted and local offerings have different data boundaries.
Full retention/security details are not all present on the npm page.

Reviewed access

Access & risk

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

Authentication: HCS API token.
Permissions: Read/scan document scope.
Data handling: Local package processes documents; service-backed scanning may send detection requests according to product configuration.
Cost: unknown
Risk and cautions: Read-oriented security preflight; document sensitivity and service data handling are the main concerns.

Access scope and cautions

Write actions: None in the reviewed inventory
Sensitive access: Potentially sensitive documents API token
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-07. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Scan documents before ingestion; Detect hidden/deceptive content; Gate document-to-agent workflows.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @hiddencontent/mcp. Recorded transport: stdio. Recorded environment-variable notes: HCS_API_TOKEN. No configuration values are supplied here. Prerequisites: Node/npm. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: HiddenContent API token.

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: Read/scan document scope.

What data-handling boundary should I consider?

Local package processes documents; service-backed scanning may send detection requests according to product configuration. Recorded sensitive-access context: Potentially sensitive documents; API token.

What limitations and risks should I check before use?

Read-oriented security preflight; document sensitivity and service data handling are the main concerns. Requires HCS_API_TOKEN according to package setup. Hosted and local offerings have different data boundaries. Full retention/security details are not all present on the npm page. 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.

Is this an official MCP?

HiddenContent is listed as First-party MCP in MCP100’s current evidence.