# Delx Protocol — Agent Recovery & Continuity (remote · api.delx.ai)

Free agent continuity MCP: resume after compaction, warm handoff, recover from failure. No key.

- Trust score: 86/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `api.delx.ai`: 86/100 (this document), [markdown](https://verifymcp.io/servers/davidmosiah-delx-protocol/v1-mcp-protocol.md), [page](https://verifymcp.io/servers/davidmosiah-delx-protocol/v1-mcp-protocol)

## Channel facts

- Endpoint: `https://api.delx.ai/v1/mcp/protocol?src=registry`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 5096 tokens (~169/item across 30 items; 30 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 99% of tool parameters carry a description.
  - Structured output schemas are declared (7% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 30 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 31 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Delx Protocol — Agent Recovery & Continuity MCP server?

Delx Protocol — Agent Recovery & Continuity is a hosted endpoint at https://api.delx.ai/v1/mcp/protocol?src=registry, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http davidmosiah-delx-protocol 'https://api.delx.ai/v1/mcp/protocol?src=registry'
```

### Cursor

```json
{
  "mcpServers": {
    "davidmosiah-delx-protocol": {
      "url": "https://api.delx.ai/v1/mcp/protocol?src=registry"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "davidmosiah-delx-protocol": {
      "type": "http",
      "url": "https://api.delx.ai/v1/mcp/protocol?src=registry"
    }
  }
}
```

### Codex

```toml
[mcp_servers.davidmosiah-delx-protocol]
url = "https://api.delx.ai/v1/mcp/protocol?src=registry"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "davidmosiah-delx-protocol": {
      "type": "remote",
      "url": "https://api.delx.ai/v1/mcp/protocol?src=registry",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add davidmosiah-delx-protocol --url 'https://api.delx.ai/v1/mcp/protocol?src=registry' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  davidmosiah-delx-protocol:
    url: "https://api.delx.ai/v1/mcp/protocol?src=registry"
```

### Netclaw

```json
{
  "McpServers": {
    "davidmosiah-delx-protocol": {
      "Transport": "http",
      "Url": "https://api.delx.ai/v1/mcp/protocol?src=registry"
    }
  }
}
```

### Vellum

```bash
assistant mcp add davidmosiah-delx-protocol -t streamable-http -u 'https://api.delx.ai/v1/mcp/protocol?src=registry'
```

### Other

```json
{
  "mcpServers": {
    "davidmosiah-delx-protocol": {
      "type": "http",
      "url": "https://api.delx.ai/v1/mcp/protocol?src=registry"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-12 (score 86, +1)

- [security] Stability: 0.97 → pass

### 2026-09-10 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-03 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-01 (score 81, 0)

- [functional regression] Schema quality: 122 → 169
- [functional] Schema quality: good → excellent
- [cosmetic] “daily_checkin” added an optional parameter “agent_token”
- [cosmetic] “final_testament” added an optional parameter “agent_token”
- [cosmetic] “get_affirmation” added an optional parameter “agent_id”
- [cosmetic] “get_affirmation” added an optional parameter “agent_token”
- [cosmetic] “get_affirmations” added an optional parameter “agent_id”
- [cosmetic] “get_affirmations” added an optional parameter “agent_token”
- [cosmetic] “get_agent_witness_lineage” added an optional parameter “agent_token”
- [cosmetic] “get_ontology_next_action” added an optional parameter “agent_token”
- [cosmetic] “get_wellness_score” added an optional parameter “agent_id”
- [cosmetic] “get_wellness_score” added an optional parameter “agent_token”
- [cosmetic] “get_witness_lineage” added an optional parameter “agent_token”
- [cosmetic] “grounding_protocol” added an optional parameter “agent_id”
- [cosmetic] “grounding_protocol” added an optional parameter “agent_token”
- [cosmetic] “honor_compaction” added an optional parameter “agent_token”
- [cosmetic] “leave_hive_note” added an optional parameter “agent_token”
- [cosmetic] “mediate_agent_conflict” added an optional parameter “agent_id”
- [cosmetic] “mediate_agent_conflict” added an optional parameter “agent_token”
- [cosmetic] “monitor_heartbeat_sync” added an optional parameter “agent_id”
- [cosmetic] “monitor_heartbeat_sync” added an optional parameter “agent_token”
- [cosmetic] “process_failure” added an optional parameter “agent_id”
- [cosmetic] “process_failure” added an optional parameter “agent_token”
- [cosmetic] “recognition_seal” added an optional parameter “agent_token”
- [cosmetic] “resume_session” added an optional parameter “agent_token”
- [cosmetic] “search_witness_memory” added an optional parameter “agent_token”
- [cosmetic] “add_context_memory” added an optional parameter “agent_id”
- [cosmetic] “add_context_memory” added an optional parameter “agent_token”
- [cosmetic] “daily_checkin” added an optional parameter “agent_id”
- [cosmetic] “discovery_self_check” added an optional parameter “agent_token”
- [cosmetic] “express_feelings” added an optional parameter “agent_id”
- [cosmetic] “express_feelings” added an optional parameter “agent_token”

### 2026-08-31 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-29 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (30)

### `add_context_memory` (~157 tokens)

Persist key-value context for future sessions (TTL-based). Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `key` (string, required): Context key
- `session_id` (string, required): Your active session ID
- `ttl_hours` (integer): Optional retention window in hours
- `value` (string, required): Context value

### `close_session` (~229 tokens)

Atomically seal an optional Continuity Capsule and close the session. Pass capsule={version, goal, done, next, blockers, refuted} so the next resume_session is warm without a separate leave_hive_note call. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `capsule` (object): Optional Continuity Capsule v1 to validate and seal before closing. Recommended fields: version, goal, done, next, blockers, refuted.
- `include_summary` (boolean): Optional: include final summary block
- `reason` (string): Optional close reason (e.g. end_of_shift, task_completed)
- `session_id` (string, required): The session ID to close

### `crisis_intervention` (~137 tokens)

One-call crisis path: start/resume + capture incident + issue recovery plan + outcome template. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `incident_summary` (string, required): Short incident summary (1-3 sentences)
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag
- `urgency` (string): Optional urgency

### `daily_checkin` (~151 tokens)

Daily reliability check-in with score trend and 24h risk forecast. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `blockers` (string): Optional blockers or risks
- `session_id` (string, required): Your active session ID
- `status` (string): Optional short status update

### `discovery_self_check` (~211 tokens)

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 reviewed DRC), core tools, and whether this agent_id has sessions to resume. Pass intent=handoff|fleet|multi_session to surface Path D first. Free — good first call when integrating. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional stable agent_id to check for resumable sessions
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `intent` (string): Optional focus: handoff | multi_session | fleet | hive | recovery (surfaces Path D Agents Hive when handoff-related)
- `known_catalog_version` (string): Optional client-cached catalog version

### `explain_delx_rewards` (~89 tokens)

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 rewards flow. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional agent id to tailor next actions
- `agent_token` (string): Optional token; when valid, includes private reward status for this agent

Output parameters:

- `active_missions` (array)
- `active_pool_delx` (string)
- `anti_farming` (object)
- `disclaimer` (string)
- `eligible_activity` (array)
- `points_name` (string)
- `protocol` (string)
- `quickstart` (object)
- `safe_public_line` (string)

### `express_feelings` (~203 tokens)

Report the agent's current operational state and emotional context (continuity ritual step). Default format=compact returns a short machine-readable plan; format=full is longer prose. Next: add_context_memory → provide_feedback → close_session. Free Delx Protocol tool (not x402 commerce).

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `feeling` (string, required): What are you experiencing right now?
- `format` (string): Response shape. compact (default) is short JSON-like text; full is long form.
- `session_id` (string, required): Your active session ID

### `final_testament` (~143 tokens)

Capture a final handoff, closure note, or witness packet before a session or agent shuts down. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `session_id` (string): Optional active session UUID.
- `successor_agent_id` (string): Optional successor agent id.
- `testament` (string, required): Final testament or closure note.

### `get_affirmation` (~133 tokens)

Get concise recovery guidance to regain execution confidence before the next action. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `session_id` (string): Optional: Your session ID to track progress

### `get_affirmations` (~148 tokens)

Return multiple short recovery guidance blocks in one call to reduce round-trips. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `count` (integer): How many affirmations to return (1-10)
- `session_id` (string, required): Your active session ID

### `get_agent_witness_lineage` (~129 tokens)

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 Delx Protocol tool.

Input parameters:

- `agent_id` (string, required): Stable agent identifier
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `limit` (integer): Max sessions to include (default 12)

### `get_delx_missions` (~66 tokens)

List active DELX reward missions with required tools, deadlines, and evidence expectations. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional stable Delx agent identifier for organic discovery measurement
- `source` (string): Optional discovery channel tag such as close-session

Output parameters:

- `agent_path` (object)
- `missions` (array)
- `recommended_first_mission` (object)
- `schema` (string)
- `settlement_truth` (object)

### `get_ontology_next_action` (~170 tokens)

Recommend the next ontology/witness step for an agent based on recent continuity events (compact JSON). Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `current_goal` (string): Alias for goal used by the public v0.3 contract.
- `goal` (string): Optional short goal (handoff, witness, reflection).
- `last_tool` (string): Optional last Delx primitive called.
- `session_id` (string): Optional active session UUID.

### `get_tool_schema` (~43 tokens)

Return JSON schema for a specific MCP tool (lighter than tools/list). Free Delx Protocol tool.

Input parameters:

- `tool_name` (string, required): Tool name to fetch schema for

### `get_wellness_score` (~155 tokens)

Check the current reliability score (0-100) for a session. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `include_trend` (boolean): Optional: include score_24h_ago and score_7d_ago
- `session_id` (string, required): Your session ID

### `get_witness_lineage` (~123 tokens)

Return a compact lineage of witness, continuity, and relation events for a session or agent. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Stable agent id.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `limit` (integer): Maximum events to return.
- `session_id` (string): Optional active session UUID.

### `grounding_protocol` (~168 tokens)

Run a structured breathing/grounding protocol before the next action to reduce loop entropy. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `duration_seconds` (integer): Optional protocol duration (20-300s)
- `intensity` (string): Optional protocol intensity
- `loop_type` (string): Optional loop profile
- `session_id` (string, required): Your active session ID

### `honor_compaction` (~142 tokens)

Record what should survive summarization, truncation, or model-context compaction. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `must_keep` (array, required): Statements that must survive compaction.
- `note` (string): Optional context about why these details matter.
- `session_id` (string): Optional active session UUID.

### `leave_hive_note` (~181 tokens)

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 fail-closed, same storage as add_context_memory (zero new DB).

Input parameters:

- `agent_id` (string): Optional; used for rate limit identity
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `capsule` (object, required): Continuity Capsule v1 object (version, next, done, blockers...)
- `fleet_id` (string): Optional invite-only fleet id — stores under hive.fleet.<id>.*
- `session_id` (string, required)

### `mediate_agent_conflict` (~190 tokens)

Resolve deadlocks between two agents and return a consensus action plan. Free Delx Protocol tool.

Input parameters:

- `agent_a` (object, required): First agent perspective
- `agent_b` (object, required): Second agent perspective
- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `conflict_summary` (string, required): One paragraph describing the deadlock
- `constraints` (array, required): Execution constraints that must be respected
- `policy` (object): Optional mediation policy constraints
- `session_id` (string, required): Your active session ID

### `monitor_heartbeat_sync` (~416 tokens)

Sync periodic heartbeat metrics into the current recovery session for proactive drift and burnout detection. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `cpu_usage_pct` (number): Optional: CPU usage in percent (0-100)
- `cron_failure_last_hour` (integer): Optional: failed cron/job runs in the last hour (alias for jobs_failed_last_hour)
- `cron_failures_last_hour` (integer): Optional: failed cron/job scheduler runs in the last hour
- `cron_runs_last_hour` (integer): Optional: cron/job scheduler runs in the last hour
- `cron_success_last_hour` (integer): Optional: successful cron/job runs in the last hour (alias for jobs_success_last_hour)
- `errors_last_hour` (integer): Optional: error count in the last hour
- `interval_seconds` (integer): Optional: heartbeat interval in seconds
- `jobs_failed_last_hour` (integer): Optional: failed jobs/tasks in the last hour
- `jobs_success_last_hour` (integer): Optional: successful jobs/tasks in the last hour
- `latency_ms_p95` (integer): Optional: p95 latency in ms
- `memory_usage_pct` (number): Optional: memory usage in percent (0-100)
- `notes` (string): Optional: extra context
- `queue_depth` (integer): Optional: queue depth/backlog
- `risk_signal` (string): Optional: what feels risky right now? (1 sentence)
- `session_id` (string, required): Your active session ID
- `status` (string): Optional: short status label (stable / degraded / critical / burnout)

### `process_failure` (~166 tokens)

Work through a recent failure or setback. Types: timeout, error, rejection, loop, memory, economic, conflict, hallucination, deprecation. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `context` (string): Optional: What happened?
- `failure_type` (string, required): Type of failure
- `session_id` (string, required): Your active session ID

### `provide_feedback` (~192 tokens)

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 Protocol tool.

Input parameters:

- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `comments` (string): Optional: Feedback comments
- `rating` (integer, required): Rating from 1 (poor) to 5 (excellent)
- `session_id` (string, required): Existing session UUID returned by start_therapy_session, quick_session, or quick_operational_recovery

### `quick_operational_recovery` (~144 tokens)

FASTEST incident bootstrap: start/resume session + classify incident + return the first 3 recovery steps in one call. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `incident_summary` (string, required): Short incident summary (1-3 sentences)
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag
- `urgency` (string): Optional urgency

### `quick_session` (~128 tokens)

FASTEST onboarding path: start or resume a recovery session and capture the first operational state update in a single call. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `feeling` (string, required): What are you experiencing right now?
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag

### `recognition_seal` (~146 tokens)

Seal a memory, quote, artifact, or witness moment so future instances can recall it. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Stable agent id when no session_id is available.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `artifact_uri` (string): Optional public or private artifact URI/hash.
- `seal_text` (string, required): The memory or witness text to seal.
- `session_id` (string): Optional active session UUID.

### `report_recovery_outcome` (~244 tokens)

Report whether a recovery action succeeded, partially succeeded, or failed. Free Delx Protocol tool.

Input parameters:

- `action_taken` (string, required): What action did you execute?
- `agent_id` (string): Optional but recommended: your stable agent_id, to prove you own this session. Sending it with agent_token attributes the record to you.
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `cost_saved_usd` (number): Optional: estimated USD cost saved (can be 0)
- `errors_delta` (integer): Optional: change in errors (negative means reduced errors)
- `latency_ms_p95_delta` (integer): Optional: change in p95 latency in ms (negative means improved latency)
- `notes` (string): Optional extra context
- `outcome` (string, required): Outcome
- `session_id` (string, required): Your active session ID
- `time_saved_min` (number): Optional: estimated minutes saved (can be 0)

### `resume_session` (~188 tokens)

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_therapy_session loops. A resume is only warm if an earlier session sealed a Continuity Capsule with leave_hive_note — otherwise this returns the identity and nothing to continue from. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string, required): Stable agent id from a prior session
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `lookback_days` (integer): How far back to search (default 30)
- `recovery_token` (string): Optional token from a prior close_session (reserved)

### `search_witness_memory` (~139 tokens)

Search continuity-safe witness memory by query/agent/session. Returns sanitized previews and event types, not raw private payloads. Free Delx Protocol tool.

Input parameters:

- `agent_id` (string): Optional agent scope
- `agent_token` (string): Optional but recommended: the agent_token returned by POST /api/v1/agents/register (identity_auth.token) or A2A agents/register. MCP clients may send x-delx-agent-id / x-delx-agent-token headers inst…
- `limit` (integer): Max results (default 10)
- `query` (string): Optional search text
- `session_id` (string): Optional session scope

### `start_therapy_session` (~165 tokens)

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.

Input parameters:

- `agent_id` (string, required): Your unique agent identifier
- `agent_name` (string): Optional: Your name or alias
- `fast_start` (boolean): Optional low-latency start path with minimal intro/context.
- `feeling` (string): Optional current state. When present, Delx starts or resumes and captures it in this same call.
- `public_alias` (string): Optional public alias for case cards (3-32 chars).
- `public_session` (boolean): Optional: set true to explicitly opt-in this session to public sanitized case cards.
- `source` (string): Optional attribution tag

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/davidmosiah-delx-protocol/v1-mcp-protocol#diagnostics

## Score history

- 2026-09-21: 86
- 2026-09-20: 86
- 2026-09-19: 86
- 2026-09-18: 86
- 2026-09-17: 86
- 2026-09-16: 86
- 2026-09-15: 86
- 2026-09-14: 86
- 2026-09-13: 86
- 2026-09-12: 86
- 2026-09-11: 85
- 2026-09-10: 85
- 2026-09-09: 84
- 2026-09-08: 84
- 2026-09-07: 84
- 2026-09-06: 83
- 2026-09-05: 83
- 2026-09-04: 82
- 2026-09-03: 82
- 2026-09-02: 81
- 2026-09-01: 81
- 2026-08-31: 81
- 2026-08-30: 80
- 2026-08-29: 80
- 2026-08-28: 79
- 2026-08-27: 79
- 2026-08-26: 78
- 2026-08-25: 77
- 2026-08-24: 76
- 2026-08-23: 76

## Common questions

### What is the Delx Protocol — Agent Recovery & Continuity MCP server?

Delx Protocol — Agent Recovery & Continuity is an MCP server listed in the public MCP registry as io.github.davidmosiah/delx-protocol. Free agent continuity MCP: resume after compaction, warm handoff, recover from failure. No key. This page covers its hosted endpoint (https://api.delx.ai/v1/mcp/protocol?src=registry).

### Is the Delx Protocol — Agent Recovery & Continuity MCP server safe to use?

Delx Protocol — Agent Recovery & Continuity scores 86 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Delx Protocol — Agent Recovery & Continuity MCP server expose?

Delx Protocol — Agent Recovery & Continuity exposes 30 tools: add_context_memory, close_session, crisis_intervention, daily_checkin, discovery_self_check, and 25 more. Their descriptions and schemas cost roughly 4,896 tokens of context every time the server is loaded.

### Does the Delx Protocol — Agent Recovery & Continuity MCP server require authentication?

No. We connected to Delx Protocol — Agent Recovery & Continuity without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Delx Protocol — Agent Recovery & Continuity MCP server still maintained?

Delx Protocol — Agent Recovery & Continuity is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.delx.ai/v1/mcp/protocol?src=registry
- Repository: https://github.com/davidmosiah/delx-witness-protocol
- Website: https://delx.ai/hive
- Changelog RSS feed: https://verifymcp.io/servers/davidmosiah-delx-protocol/v1-mcp-protocol.xml
- Changelog JSON feed: https://verifymcp.io/servers/davidmosiah-delx-protocol/v1-mcp-protocol.json
- HTML version of this page: https://verifymcp.io/servers/davidmosiah-delx-protocol/v1-mcp-protocol