cliwant

Human-in-the-loop approval queue for tool-using agents. The agent enqueues an action it wants to take (send email, push commit, file return, charge card); a human reviews and approves/rejects/modifies; the agent picks up the verdict on the next turn. Backed by the @cliwant/mcp-approval-queue MCP server. Triggers on phrases like "queue this for approval", "review this before sending", "wait for human approval", "검토해줘", "승인", "確認して", "承認", or whenever Claude is about to take a real-world action that should not happen unsupervised.

Three-tier persistent memory (digest / working-set / long-term vector) for any Claude / Codex / Gemini session. Records the user's preferences, decisions, and project facts so they survive across sessions. Backed by the @cliwant/mcp-memory-tiers MCP server. Triggers on phrases like "remember this", "what did we decide about", "기억해줘", "覚えておいて", or whenever Claude needs persistent memory beyond the current session.

Query and analyze US federal contracting + spending + regulation data. 52 keyless tools across SAM.gov (active + pre-solicitation opportunities, RFPs, attachment TEXT extraction, contacting officers), USAspending.gov (awards, recipients, sub-agencies, time-series, NAICS/PSC analysis, recompete + incumbent pressure), Federal Register (rules, notices), eCFR + FAR/DFARS compliance (clause lookup, compliance matrix), SBA size standards, Grants.gov (federal grants), pricing & wage determinations (SCA/DBA + GSA CALC), and integrity/teaming/protests (exclusions, teaming partners, GAO protests). Use when the user asks about federal contracts, GovCon opportunities, SAM.gov notices, contracting officers, RFP / SOW analysis, reading the actual solicitation documents, FAR/DFARS clause compliance, agency spending, recompete signals, recipient win history, subawards, vetting a firm or teaming partner, bid pricing / wage floors, federal regulations, FAR clauses, federal grants, or any US Government procurement / spending qu