SpendShield
PulseGate's liveness check found it on 3 Oct 2026; it has been in the index since 31 Aug 2026. How this is checked
SpendShield is an open-source Python security layer for AI-agent payments. It provides spend-capped identities, intent and policy checks, prompt-injection defenses, secret-handling controls, and MCP integration for developers building agentic payment workflows.
Inferred · not functionally tested
Overview
6 featuresPurpose: Preventing AI agents from making unauthorized or excessive payments.
Inferred · not functionally tested
Audience: developers building AI agents and payment workflows
Inferred · not functionally tested
Functions: payments, agents
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Open Source · platforms: CLI, WEB · deployment: browser, cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: github.com. These links do not verify the individual claims.
SpendShield sits in PulseGate's AI security & guardrails category. Inferred · not functionally tested: It focuses on preventing AI agents from making unauthorized or excessive payments. Inferred · not functionally tested: SpendShield is an open-source project aimed at developers building AI agents and payment workflows. Basis unknown · not verified: SpendShield is open source under the Open Source license. Basis unknown · not verified: It ships for the web, the command line, and API, and it can be self-hosted.
Behind SpendShield is felixpg13-glitch. Inferred · not functionally tested: Among its 6 catalogued features are spend caps, payment policies, and intent verification. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Spend caps
- Payment policies
- Intent verification
- Prompt injection defense
- Secret protection
- MCP integration
Topics: Inferred · not functionally tested
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed31 Aug · 20:21 UTCShow HN: My AI spent $15 on a test order, so I built a payment guardrail seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about SpendShield
- What is SpendShield?
- Inferred · not functionally tested: SpendShield focuses on preventing AI agents from making unauthorized or excessive payments. It is catalogued under AI security & guardrails on PulseGate.
- Who is SpendShield for?
- Inferred · not functionally tested: SpendShield is an open-source project built for developers building AI agents and payment workflows.
- Does SpendShield have a free plan?
- Basis unknown · not verified: Yes — SpendShield is open source under the Open Source license and free to use.
- What platforms does SpendShield run on?
- Basis unknown · not verified: SpendShield runs on the web, the command line, and API. It can also be self-hosted.
- Is SpendShield still active?
- PulseGate's liveness check found it on 3 Oct 2026.
- Who develops SpendShield?
- SpendShield is developed by felixpg13-glitch.
- Is SpendShield open source?
- Basis unknown · not verified: Yes — SpendShield is open source under the Open Source license.
- Does SpendShield have an API or integrations?
- Inferred · not functionally tested: Yes — SpendShield exposes an MCP server.
Similar projects
Closest matches by what these projects do