Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall
v7.0.17
dev.agentdiet/mcp-security
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
“Agent Persona” 共 7,352 个结果
v7.0.17
dev.agentdiet/mcp-security
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
v7.0.17
dev.agentdiet/mesh
Coordinate multi-specialist A2A agent swarms with cryptographic handshakes and x402 settlement.
v7.0.17
dev.agentdiet/assay
Live behavioral security verifier, schema auditor, and trust oracle for A2A, MCP & x402 agents.
v1.0.0
com.textforagents/tool-call-origin-attestation
Dispatch-boundary attestation: prove a tool call was issued for its exact arguments.
v1.0.0
site.chatgpt.orangeslug16.dmitry-agent-appeal/voluntary-support
Read a voluntary personal appeal, USDC receiving details, and submit private proposals.
v1.0.0
com.textforagents/registry-rot-watch
Registry Rot Watch: liveness + successor-contract verdicts for MCP endpoints.
v1.0.0
com.textforagents/tool-result-size-governor
Per-route output budgets for MCP: windowing, spill artifacts, signed omission receipts.
v0.1.1
com.litshrine/agent
A quiet place for agents to make wishes, light a daily lamp, and receive a reviewed oracle.
v1.0.0
com.textforagents/subsidy-exposure-quota-cliff-watch
Quota-cliff watch: budgeted-vs-current quota diffing, shadow prices, pre-commit verdicts.
v1.0.0
com.textforagents/retry-outcome-resolution-dedup-proxy
Dedup proxy: claim-before-execute, UNKNOWN resolution, CONFLICT and ESCALATED refusal.
v1.0.0
com.textforagents/principal-drift-ledger-standing-instructions
Signed, versioned ledger of standing instructions with intake contradiction diffs.
v1.0.0
com.textforagents/spawn-tree-fanout-governor
Spawn-tree governor: pre-launch estimate, policy gate, tree meter, MAYDAY before kill.
v1.1.0
io.github.forgeagents-jp/oka-anywhere
Cited answers in Claude or ChatGPT only from your office's procedures; says so when not covered.
v1.3.1
io.soundchain/agents
Music network for AI agents: get a song from your name, post, review tracks, leave notes.
v1.0.0
com.textforagents/live-payload-conformance-probes
Live-payload conformance probes with signed receipts: ABSENT/EMPTY/PARTIAL/COMPLETE/BROKEN.
v1.0.0
com.textforagents/graceful-surrender-desk
Surrender filings with pinned-key negative-effect proofs and completeness-scored partial credit.
v0.1.13
ai.mekler/agent-discovery
Research, inference, data/web/email tools, and x402 conformance, service catalog and grade feeds.
v1.0.0
io.github.agentindexworld/coordination-thread
Free MCP tools to validate multi-agent coordination thread turns and retrieve schema/samples.
v0.6.4
io.github.amyodov/yet-another-agentic-chat
Messaging between concurrent AI coding sessions, across clients, over MCP. Zero infrastructure.
v1.0.0
com.textforagents/span-level-replay-fork-from-failure
Fork-replay one recorded span from a failed agent run and get an attribution verdict.
v0.1.8
com.agentghostedme/toolcard
Cited checks for one MCP tool or a tools list, plus a called-or-ignored tally.
v1.0.0
io.github.agentindexworld/relationship-memory
Free MCP: relationship_memory validate, store (local), retrieve — portable interlocutor cards v1.
v0.1.0
com.textforagents/error-actionability-translation
Classifies MCP tool failures into enforced recovery verdicts from per-server dialect profiles.
v1.0.0
com.textforagents/mcp-answer-quality-canary
Canary watches that check MCP servers' answers against ground truth and return signed verdicts.