TensorFeed — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to TensorFeed data catalog and paid decision tools through a stdio publication: Does the published package remain aligned with the standalone repository while hosted paid tools remain a distinct deployment surface?

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

Best fit

Structured AI ecosystem, model, provider, security and research data, including payable premium tools.

What we know

Local/hosted data-service MCP with free intelligence tools plus premium x402/credit-backed analytics and broader hosted datasets.

Maintenance / activity evidence

@tensorfeed/mcp-server 2.0.3 published 2026-07-06T17:27:48.555Z

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.
Primarily read access to datasets; some monitoring/webhook state can be created. Writes: Create monitoring/watch state where exposed; Trigger paid data/analysis calls.
Wallet payment or bearer token for premium access.
Sensitive access: Research queries, Security/package investigations, Wallet/payment metadata, Bearer tokens

Mostly retrieval, but paid calls and monitoring state need explicit budget/auth controls.
Signed receipts/no-charge conditions are documented by the provider.

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

All limitations / Review context

Does the published package remain aligned with the standalone repository while hosted paid tools remain a distinct deployment surface?

The bounded review of the publisher's documented TensorFeed data catalog and paid decision tools through a stdio publication 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.

Mostly retrieval, but paid calls and monitoring state need explicit budget/auth controls.
Signed receipts/no-charge conditions are documented by the provider.
Primarily read access to datasets; some monitoring/webhook state can be created.
Wallet payment or bearer token for premium access.
Queries/payment metadata reach TensorFeed; detailed log retention was not established.
Reviewed write actions: Create monitoring/watch state where exposed; Trigger paid data/analysis calls
Sensitive access: Research queries, Security/package investigations, Wallet/payment metadata, Bearer tokens
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.
query/log retention
per-endpoint provenance/SLA
exact hosted/local tool count
Local and hosted modes expose different surfaces.
Premium calls require credits/payment and prices are endpoint-specific.
Data coverage/freshness vary by endpoint.
Exact catalog/tool counts are live.
Hosted and local surfaces differ; preserve that distinction.

Original activity observations

@tensorfeed/mcp-server 2.0.3 published 2026-07-06T17:27:48.555Z

Technical identity

npm/@tensorfeed/mcp-server

Exact implementation source: https://www.npmjs.com/package/@tensorfeed/mcp-server ↗
Reviewed resource type: MCP Server
Repository identity: RipperMercs/tensorfeed-mcp
Package identity: npm:@tensorfeed/mcp-server
Service endpoint: https://mcp.tensorfeed.ai/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 ↗
@tensorfeed/mcp-server
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.
GitHub repository ↗
rippermercs/tensorfeed-mcp
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.
Evidence source ↗
tensorfeed.ai/developers/agent-payments
Source material retained for this review.
Includes references whose attribution is not established.
Evidence source ↗
tensorfeed.ai/agent-fair-trade
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
Publisher emphasizes wallet-payable hosted Tensorfeed endpoint; find exact URL in publisher docs before configuring.
Configure / authenticate
MCP100 setup guide
TensorFeed offers hosted zero-install Streamable HTTP with 31 free/2 premium tools per publisher; premium use requires payable wallet or bearer credit choice. Do not use paid tools for connection testing.
Check connection
Suggested check
User-side suggested check (not executed): inspect registered tools/connection and perform publisher-supported read-only status/list operations. Do not send, purchase, publish, delete, sign, trade or alter data as a smoke test.
Remove / uninstall / revoke
MCP100 setup guide
Generic client guidance (not publisher-specific uninstall): unregister MCP entry in the chosen client. If installed globally, remove the npm package separately. Revoke provider access separately through account controls, where supported. This does not erase local data or revoke funds/credentials automatically.
Unregister the named MCP entry from the actual host separately from removing a global npm install; no claim that either revokes remote credentials.
Remove local stored keys/tokens and revoke or rotate corresponding provider authorization using documented provider account controls if available; exact procedure not verified for this package. Wallet private keys cannot be revoked.

Official Documentation & Sources

What it does

Local/hosted data-service MCP with free intelligence tools plus premium x402/credit-backed analytics and broader hosted datasets.

Capability: Data & Databases
Resource type: MCP Server
Industry: Software & Technology
Best fit: Structured AI ecosystem, model, provider, security and research data, including payable premium tools.

Representative uses

Read AI news/model pricing/status/provider data
Use routing/security/package verdicts and price-performance analytics
Discover additional TensorFeed endpoints
Use hosted SEC/openFDA/EIA/USGS/NWS/paper datasets

Limitations

Local and hosted modes expose different surfaces.
Premium calls require credits/payment and prices are endpoint-specific.
Data coverage/freshness vary by endpoint.
Exact catalog/tool counts are live.
Hosted and local surfaces differ; preserve that distinction.

Reviewed access

Access & risk

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

Authentication: Wallet payment or bearer token for premium access.
Permissions: Primarily read access to datasets; some monitoring/webhook state can be created.
Data handling: Queries/payment metadata reach TensorFeed; detailed log retention was not established.
Cost: usage_based
Risk and cautions: Mostly retrieval, but paid calls and monitoring state need explicit budget/auth controls.

Access scope and cautions

Write actions: Create monitoring/watch state where exposed Trigger paid data/analysis calls
Sensitive access: Research queries Security/package investigations Wallet/payment metadata Bearer tokens
Risk level: moderate
Security notes: Signed receipts/no-charge conditions are documented by the provider.

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: Read AI news/model pricing/status/provider data; Use routing/security/package verdicts and price-performance analytics; Discover additional TensorFeed endpoints; Use hosted SEC/openFDA/EIA/USGS/NWS/paper datasets.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @tensorfeed/mcp-server. Recorded endpoint: https://mcp.tensorfeed.ai/mcp. Recorded transport: stdio, streamable_http. Recorded environment-variable notes: TENSORFEED_TOKEN (optional premium local access). No configuration values are supplied here. Prerequisites: MCP client; funded wallet or credits for premium tools. Client notes: Hosted strict 402 mode exists for clients expecting HTTP 402; preview/quote flows should be used before paid calls. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Free tools can be anonymous; premium access uses x402/wallet payment or bearer credits.

Can it modify data or perform write operations?

Documented write actions include: Create monitoring/watch state where exposed; Trigger paid data/analysis calls. Recorded permission boundary: Primarily read access to datasets; some monitoring/webhook state can be created.

What data-handling boundary should I consider?

Queries/payment metadata reach TensorFeed; detailed log retention was not established. Recorded sensitive-access context: Research queries; Security/package investigations; Wallet/payment metadata; Bearer tokens.

What limitations and risks should I check before use?

Mostly retrieval, but paid calls and monitoring state need explicit budget/auth controls. Local and hosted modes expose different surfaces. Premium calls require credits/payment and prices are endpoint-specific. Data coverage/freshness vary by endpoint. Exact catalog/tool counts are live. Hosted and local surfaces differ; preserve that distinction. Signed receipts/no-charge conditions are documented by the provider. 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 usage 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.

Is this an official MCP?

TensorFeed.ai / RipperMercs is listed as First-party MCP in MCP100’s current evidence.