prompt-protection vs Propagation breaker for agent fleets
prompt-protection is an open-source MCP server for ai models and llm tooling. Propagation breaker for agent fleets is a paid MCP server for security.
- prompt-protection is open source, while Propagation breaker for agent fleets is paid.
- prompt-protection is open source; Propagation breaker for agent fleets is not.
- prompt-protection is best for block an email-borne url from reaching an outbound request.
- Propagation breaker for agent fleets is best for screen messages between agents for worm-like payloads.
- What it is
- prompt-protection is an open-source MCP server for ai models and llm tooling.Propagation breaker for agent fleets is a paid MCP server for security.
- Best for
- Block an email-borne URL from reaching an outbound requestScreen messages between agents for worm-like payloads
- Kind
- MCP serverMCP server
- Pricing
- Open sourcePaid, from $19 a month
- Platforms
- CLI, self-hosted, WebAPI
- Runs
- LocallyRemotely
- Open source
- Good for
- Block an email-borne URL from reaching an outbound request; Scan user input for jailbreaks before it reaches a model; Check model output for leaked system prompts or API keysScreen messages between agents for worm-like payloads; Watch a fleet for propagation of one payload; Prevent shared memory writes from becoming instructions
What prompt-protection does
Tool-call guard
Checks each proposed tool call and blocks untrusted data reaching exfiltration or exec sinks.
Provenance tracking
Labels tool results as untrusted and tracks trusted destinations the user named.
Input normalisation
Folds Unicode, strips hidden characters and decodes base64 and URL encoding before matching.
Output scanning
20 rules check responses for leaked prompts, credentials, relayed injections and PII.
Three-way verdicts
Returns allow, flag or block so medium-confidence hits can be logged.
Framework wrappers
Includes an Express middleware, a Next.js App Router wrapper and a React hook.
What Propagation breaker for agent fleets does
Egress quarantine
Holds or blocks outbound messages that copy instructions from inbound context.
Outbreak telemetry
Alerts when a fingerprint reaches three or more agents, with an R estimate.
Data-only shared store
Writes cannot become instructions without a bound cryptographic token.
Fingerprint query
Agents can ask whether a payload has been seen propagating.
Control verification
A sealed registry detects tampering with the breaker's own controls.
LangGraph adapter
Screens messages inside StateGraph transitions.
prompt-protection vs Propagation breaker for agent fleets: questions
Is prompt-protection or Propagation breaker for agent fleets cheaper?
prompt-protection is the cheaper option: it is open source.
What is the difference between prompt-protection and Propagation breaker for agent fleets?
prompt-protection is an open-source MCP server for ai models and llm tooling. Propagation breaker for agent fleets is a paid MCP server for security. prompt-protection is open source, while Propagation breaker for agent fleets is paid. prompt-protection is open source; Propagation breaker for agent fleets is not.
