← Back
Home › Systems › Agentic AI

mcp-host

MCP host that connects many tool servers

Claude Desktop

SystemTechniques · 19Primitives · 84 mcp-host Model context protocolagentic-ai · medium: JSON-RPC protocol exposing tools, resources and prompts from servers to LLM clients, with capability negotiationPrompt injection defenseagentic-ai · medium: Treat every untrusted string as data, track where values came from, and make tool calls and rendered output depend on provenance, not on what the model says.›Tool retrieval (selecting tools for…agentic-ai · medium: Index tool descriptions, filter by the caller's permissions, rank against the request and put only the top few definitions in context, in a stable order.›Deterministic simulation testingdistributed · medium: Run the whole system in one thread under a seeded scheduler with simulated network, disk and clock, so every failure replays from its seed.›Primary-backup replicationdistributed · medium: One node orders all writes and ships them to standbys; the acknowledgement rule (none, one, all) sets what a crash loses, and an external arbiter decides who takes over.›Coverage-guided fuzzingsecurity · medium: Mutate inputs, run an instrumented target, and keep any input that reaches a new code edge; feedback turns blind guessing into incremental search.›Process sandboxingsecurity · medium: Run risky work in a separate, deliberately powerless process and let a small privileged broker do the few things it needs, over a narrow pipe.›Json rpcnetworking · low: JSON-RPC 2.0 requests, notifications and batchingServer-sent eventsnetworking · low: One long-lived HTTP response carries text events one way; each event may carry an id, so a reconnecting client names its last one and the server resumes.›JSON Schema validationsecurity · low: Compile a JSON Schema once, then check every untrusted document against it, within hard size and depth limits, and report failures as JSON Pointers.›OAuth 2 and OpenID Connectsecurity · low: Delegated authorization (OAuth 2) and login on top of it (OIDC); use authorization code + PKCE for every user-facing client.›Least privilege and isolationsecurity · low: Assume every component will be compromised and limit what it can then reach: narrow identities, separate accounts, sandboxed processes.›Embeddingsmachine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.›Agent loopagentic-ai · unknown: Agent sandboxingagentic-ai · unknown: Context window managementagentic-ai · low: Keep an agent's growing history inside the model's window by truncating, clearing and summarizing old turns in a cheap-to-lossy ladder, at turn boundaries.›Tool callingagentic-ai · low: The model emits a structured call (id, name, JSON arguments) instead of prose; your code validates, runs it and returns a result tagged with the same id.›Hdr histogramdata-structures · low: Log-linear bucketed histograms with bounded relative error for latency percentilesProcess supervisionhardware-os · low: A parent process starts services, reaps their exits and restarts them under a delay and burst-limit policy, then stops them with SIGTERM before SIGKILL.›Capability-based security (object c…security · low: Authority is a handle you hold, not an identity you have: code can only act on objects it was explicitly given handles to, and handles can only be narrowed and passed on.›Hardware backed keystoresecurity · low: Non-exportable keys in Secure Enclave, StrongBox, TPM: generation, use policies, biometric gatingMutual TLSsecurity · low: TLS where the client also proves a certificate key, so every connection carries a verified, rotatable machine identity.›Secrets managementsecurity · low: Keep keys and passwords out of code and logs, give workloads short-lived identity instead of static keys, and make rotation routine.›+ 12 more techniques+ 68 more primitives

Similar systems

Share the most building blocks with this one.

agent-runtime 56 %mcp-server 48 %agent-gateway 40 %computer-use-agent 37 %reverse-etl 35 %