PolicyForge MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to PolicyForge legal-policy generation and freshness checks: Do generated policies retain jurisdiction and source limitations rather than imply legal compliance certification?

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

Best fit

Generate, audit and maintain legal policies that match the application's actual code/data practices.

What we know

PolicyForge MCP exposes policy generation, BAA generation, compliance auditing, freshness/drift checks and broader policy/consent API operations. Local stdio uses an API key; remote endpoint supports authenticated HTTP/OAuth-style access.

Maintenance / activity evidence

@policyforge/mcp 0.8.0 published 2026-09-29T13:34:08.808Z

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.
Policy generation/audit plus hosted policy/consent/webhook state depending on exposed tools. Writes: Generate/regenerate hosted policies; Potentially manage consent/webhook/policy state.
API key or remote authenticated session.
Sensitive access: Source/code practice details, Legal policies, Consent records, API key

Legal/compliance output can affect user disclosures; human/legal review remains necessary.

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

All limitations / Review context

Do generated policies retain jurisdiction and source limitations rather than imply legal compliance certification?

The bounded review of the publisher's documented PolicyForge legal-policy generation and freshness checks 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.

Legal/compliance output can affect user disclosures; human/legal review remains necessary.
Policy generation/audit plus hosted policy/consent/webhook state depending on exposed tools.
API key or remote authenticated session.
Code/app data, generated policies and consent records may be processed/stored by PolicyForge.
Reviewed write actions: Generate/regenerate hosted policies; Potentially manage consent/webhook/policy state
Sensitive access: Source/code practice details, Legal policies, Consent records, API key
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.
Generated policies are not a substitute for legal counsel.
Codebase context may be sent for generation/audit.
Some broader API operations can alter hosted policy/consent/webhook state.
Authentication mode differs between local API-key and remote service.
Do not present generated legal text as legal advice or compliance guarantee.

Original activity observations

@policyforge/mcp 0.8.0 published 2026-09-29T13:34:08.808Z

Technical identity

npm/@policyforge/mcp

Exact implementation source: https://www.npmjs.com/package/@policyforge/mcp ↗
Reviewed resource type: MCP Server
Repository identity: PolicyForge/mcp
Package identity: npm:@policyforge/mcp
Service endpoint: https://policyforge.co/api/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 ↗
@policyforge/mcp
Recorded package identity, distribution or download evidence.
Evidence source ↗
policyforge.co/documentation
Source material retained for this review.
Includes references whose attribution is not established.
Evidence source ↗
policyforge.co/api/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.

Install / connect
Publisher instructions
OAuth remote is preferred; key-header remote and local POLICYFORGE_API_KEY routes also documented.
publisher install or stdio launch · Claude Code only · Publisher instructions
claude mcp add -s user --transport http policyforge https://policyforge.co/api/mcp
Configure / authenticate
MCP100 setup guide
PolicyForge documents remote OAuth, remote API-key and local API-key alternatives; choose one, do not merge their configurations.
Check connection
Suggested check
Select publisher free/read-only compliance inspection or check_policy_freshness only; do not generate paid legal policies or alter compliance documents.
Remove / uninstall / revoke
MCP100 setup guide
If you added this integration to Claude Code under the registration name `policyforge`, run `claude mcp remove policyforge` 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: PolicyForge documents API-key invalidation by deleting/disabling the key (401) and OAuth access revocation; exact per-client account UI label not confirmed. Keep remote OAuth versus static-key steps separate.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove policyforge

Official Documentation & Sources

What it does

PolicyForge MCP exposes policy generation, BAA generation, compliance auditing, freshness/drift checks and broader policy/consent API operations. Local stdio uses an API key; remote endpoint supports authenticated HTTP/OAuth-style access.

Capability: Security & Testing
Resource type: MCP Server
Industry: Legal & Compliance
Best fit: Generate, audit and maintain legal policies that match the application's actual code/data practices.

Representative uses

Generate privacy/terms/cookie/refund/EULA policies
Generate HIPAA BAA
Audit code/policy gaps
Check policy freshness/drift
Read usage/quota

Limitations

Generated policies are not a substitute for legal counsel.
Codebase context may be sent for generation/audit.
Some broader API operations can alter hosted policy/consent/webhook state.
Authentication mode differs between local API-key and remote service.
Do not present generated legal text as legal advice or compliance guarantee.

Reviewed access

Access & risk

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

Authentication: API key or remote authenticated session.
Permissions: Policy generation/audit plus hosted policy/consent/webhook state depending on exposed tools.
Data handling: Code/app data, generated policies and consent records may be processed/stored by PolicyForge.
Cost: plan_based
Risk and cautions: Legal/compliance output can affect user disclosures; human/legal review remains necessary.

Access scope and cautions

Write actions: Generate/regenerate hosted policies Potentially manage consent/webhook/policy state
Sensitive access: Source/code practice details Legal policies Consent records API key
Risk level: high

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: Generate privacy/terms/cookie/refund/EULA policies; Generate HIPAA BAA; Audit code/policy gaps; Check policy freshness/drift; Read usage/quota.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @policyforge/mcp@latest. Recorded endpoint: https://policyforge.co/api/mcp. Recorded transport: stdio, streamable_http. Recorded environment-variable notes: POLICYFORGE_API_KEY (local); POLICYFORGE_API_URL (optional). No configuration values are supplied here. Prerequisites: PolicyForge account; MCP client. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Local bearer API key; remote service requires authenticated grant/token.

Can it modify data or perform write operations?

Documented write actions include: Generate/regenerate hosted policies; Potentially manage consent/webhook/policy state. Recorded permission boundary: Policy generation/audit plus hosted policy/consent/webhook state depending on exposed tools.

What data-handling boundary should I consider?

Code/app data, generated policies and consent records may be processed/stored by PolicyForge. Recorded sensitive-access context: Source/code practice details; Legal policies; Consent records; API key.

What limitations and risks should I check before use?

Legal/compliance output can affect user disclosures; human/legal review remains necessary. Generated policies are not a substitute for legal counsel. Codebase context may be sent for generation/audit. Some broader API operations can alter hosted policy/consent/webhook state. Authentication mode differs between local API-key and remote service. Do not present generated legal text as legal advice or compliance guarantee. 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.

What cost model is recorded?

The reviewed cost model is plan based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.