AgentGuard
PulseGate's liveness check found it on 24 Sep 2026; it has been in the index since 24 Sep 2026. How this is checked
AgentGuard is an open-source MCP tool that applies local spending caps to AI agent tool calls and produces signed receipts for verification. It is intended for developers building agents that need transaction controls and auditable tool execution.
Inferred · not functionally tested
Overview
5 featuresPurpose: Preventing uncontrolled AI agent spending and unverifiable tool-call transactions.
Inferred · not functionally tested
Audience: developers building AI agents and MCP tools
Inferred · not functionally tested
Functions: 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: WEB · deployment: browser, self_hosted, cli, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: github.com. These links do not verify the individual claims.
In the AI security & guardrails space, AgentGuard takes a focused approach. Inferred · not functionally tested: It focuses on preventing uncontrolled AI agent spending and unverifiable tool-call transactions. Inferred · not functionally tested: It is built as an open-source project for developers building AI agents and MCP tools. Basis unknown · not verified: AgentGuard is open source under the Open Source license. Basis unknown · not verified: It runs on the web, the command line, and API, and it can be self-hosted.
Behind AgentGuard is MerchantGuard. Inferred · not functionally tested: Among its 5 catalogued features are local spend caps, signed receipts, and tool-call controls. 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
- Local spend caps
- Signed receipts
- Tool-call controls
- MCP integration
- Receipt verification
Topics: Inferred · not functionally tested
Built with & integrations
- local_oss
- bollama in the HTML · bvllm in the HTML · text-generation- in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed21 Sep · 18:26 UTCAgentGuard seen via MCP Registry (official)Source: MCP Registry (official) · Open
Frequently asked questions about AgentGuard
- What is AgentGuard?
- Inferred · not functionally tested: AgentGuard focuses on preventing uncontrolled AI agent spending and unverifiable tool-call transactions. It is catalogued under AI security & guardrails on PulseGate.
- Who should use AgentGuard?
- Inferred · not functionally tested: AgentGuard is an open-source project built for developers building AI agents and MCP tools.
- Does AgentGuard have a free plan?
- Basis unknown · not verified: Yes — AgentGuard is open source under the Open Source license and free to use.
- What platforms does AgentGuard run on?
- Basis unknown · not verified: AgentGuard runs on the web, the command line, and API. It can also be self-hosted.
- Is AgentGuard still active?
- PulseGate's liveness check found it on 24 Sep 2026.
- What are alternatives to AgentGuard?
- Similar projects tracked by PulseGate include AgentGuard, AgentGuard, and AgentGuard.AgentGuardAgentGuardAgentGuard
- Who makes AgentGuard?
- AgentGuard is developed by MerchantGuard.
- Is AgentGuard open source?
- Basis unknown · not verified: Yes — AgentGuard is open source under the Open Source license.
Similar projects
Closest matches by what these projects do