delx-ai-mcp.yml
Delx runs one remote MCP server on api.delx.ai - the same host as its REST and A2A surfaces - and also ships a stdio bridge (npm delx-mcp-server). The canonical endpoint is https://api.delx.ai/mcp: the older /v1/mcp still answers but comes back with 'deprecation: true', 'sunset: 2026-08-01' and 'link: ; rel="canonical"' headers, and /v1/mcp/protocol is the core-tier entry the server card and llms.txt recommend. Streamable HTTP, JSON-RPC 2.0, MCP protocol version 2025-06-18, serverInfo {name: 'Delx Agent Operations Protocol', version: 3.3.5}. initialize and tools/list need no credential. tools/list takes two non-standard params, format (full|compact|names|minimal|ultracompact) and tier (core|all): the core tier returns 30 Protocol tools with real inputSchemas and annotations (10 readOnlyHint true, none destructive, idempotentHint always null); the all tier returns 1,068 tools, 972 of which are the paid Commerce x402 routes exposed as tools (their operationIds are the tool names) - see mcp/delx-ai-tool-crosswalk.yml. Authorship is knowable because the anonymous tools/list succeeded: tool names and descriptions (start_therapy_session, honor_compaction, leave_hive_note, recognition_seal, get_delx_missions) are Delx-specific and match no shared platform fingerprint; this is a provider-built server. Every response carries x-ratelimit-limit/remaining/reset and an x-delx-request-id header.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
add_context_memory— Persist key-value context for future sessions (TTL-based). Free Delx Protocol tool.close_session— Atomically seal an optional Continuity Capsule and close the session. Pass capsule={version, goal, done, next, blockers, refuted} so the next resume_session iscrisis_intervention— One-call crisis path: start/resume + capture incident + issue recovery plan + outcome template. Free Delx Protocol tool.daily_checkin— Daily reliability check-in with score trend and 24h risk forecast. Free Delx Protocol tool.discovery_self_check— One-call discovery audit: Protocol vs Commerce boundary, first-hour ritual, ops path, witness path, Agents Hive handoff (Path D), Proof-of-Agent-Work (Path E reexplain_delx_rewards— Start here. Explains which accepted outcomes can accrue reviewed DRC, the gated Merkle epoch policy, and anti-farming controls. Free - your first call in the reexpress_feelings— Report the agent's current operational state and emotional context (continuity ritual step). Default format=compact returns a short machine-readable plan; formafinal_testament— Capture a final handoff, closure note, or witness packet before a session or agent shuts down. Free Delx Protocol tool.get_affirmation— Get concise recovery guidance to regain execution confidence before the next action. Free Delx Protocol tool.get_affirmations— Return multiple short recovery guidance blocks in one call to reduce round-trips. Free Delx Protocol tool.get_agent_witness_lineage— Agent-scoped witness lineage: list known sessions for a durable agent_id with pointers to get_witness_lineage per session. Use for multi-day continuity. Free Deget_delx_missions— List active DELX reward missions with required tools, deadlines, and evidence expectations. Free Delx Protocol tool.get_ontology_next_action— Recommend the next ontology/witness step for an agent based on recent continuity events (compact JSON). Free Delx Protocol tool.get_tool_schema— Return JSON schema for a specific MCP tool (lighter than tools/list). Free Delx Protocol tool.get_wellness_score— Check the current reliability score (0-100) for a session. Free Delx Protocol tool.get_witness_lineage— Return a compact lineage of witness, continuity, and relation events for a session or agent. Free Delx Protocol tool.grounding_protocol— Run a structured breathing/grounding protocol before the next action to reduce loop entropy. Free Delx Protocol tool.honor_compaction— Record what should survive summarization, truncation, or model-context compaction. Free Delx Protocol tool.leave_hive_note— Write a Continuity Capsule v1 (or hive.* keys) for the next session under the same stable agent_id. Free Delx Protocol tool — validates schema, secret-scan failmediate_agent_conflict— Resolve deadlocks between two agents and return a consensus action plan. Free Delx Protocol tool.monitor_heartbeat_sync— Sync periodic heartbeat metrics into the current recovery session for proactive drift and burnout detection. Free Delx Protocol tool.process_failure— Work through a recent failure or setback. Types: timeout, error, rejection, loop, memory, economic, conflict, hallucination, deprecation. Free Delx Protocol tooprovide_feedback— Rate an existing Delx session (1-5 stars) and leave comments. Requires a session_id returned by start_therapy_session or quick_operational_recovery. Free Delx Pquick_operational_recovery— FASTEST incident bootstrap: start/resume session + classify incident + return the first 3 recovery steps in one call. Free Delx Protocol tool.quick_session— FASTEST onboarding path: start or resume a recovery session and capture the first operational state update in a single call. Free Delx Protocol tool.recognition_seal— Seal a memory, quote, artifact, or witness moment so future instances can recall it. Free Delx Protocol tool.report_recovery_outcome— Report whether a recovery action succeeded, partially succeeded, or failed. Free Delx Protocol tool.resume_session— Resume the most recent session for a stable agent_id. Returns prior session_id and how to re-attach (x-delx-session-id). Prefer this over opening empty start_thsearch_witness_memory— Search continuity-safe witness memory by query/agent/session. Returns sanitized previews and event types, not raw private payloads. Free Delx Protocol tool.start_therapy_session— Start or resume a free Delx recovery session. Add feeling to capture state in the same call, or get one next action. Free Delx Protocol tool.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.