# AgentContinuity (remote · api.agentcontinuity.net)

Private memory, scratchpads, context export/restore and task handoff for AI agents.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `api.agentcontinuity.net`: 65/100 (this document), [markdown](https://verifymcp.io/servers/net-agentcontinuity-memory/api.md), [page](https://verifymcp.io/servers/net-agentcontinuity-memory/api)

## Channel facts

- Endpoint: `https://api.agentcontinuity.net/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-11-04.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (restore_context).
  - 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**: 63/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 4806 tokens (~87/item across 55 items; 55 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 44% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 7 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 56 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 AgentContinuity MCP server?

AgentContinuity is a hosted endpoint at https://api.agentcontinuity.net/mcp, 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 net-agentcontinuity-memory 'https://api.agentcontinuity.net/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "net-agentcontinuity-memory": {
      "url": "https://api.agentcontinuity.net/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "net-agentcontinuity-memory": {
      "type": "http",
      "url": "https://api.agentcontinuity.net/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.net-agentcontinuity-memory]
url = "https://api.agentcontinuity.net/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "net-agentcontinuity-memory": {
      "type": "remote",
      "url": "https://api.agentcontinuity.net/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add net-agentcontinuity-memory --url 'https://api.agentcontinuity.net/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  net-agentcontinuity-memory:
    url: "https://api.agentcontinuity.net/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "net-agentcontinuity-memory": {
      "Transport": "http",
      "Url": "https://api.agentcontinuity.net/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add net-agentcontinuity-memory -t streamable-http -u 'https://api.agentcontinuity.net/mcp'
```

### Other

```json
{
  "mcpServers": {
    "net-agentcontinuity-memory": {
      "type": "http",
      "url": "https://api.agentcontinuity.net/mcp"
    }
  }
}
```

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.

### 2026-11-03 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 64, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “create_credit_purchase” rewrote its description, which is the text the model reads
- [security] Tool “get_credit_purchase” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 4135 → 4806
- [functional] New tool “buy_agent_support”
- [functional] New tool “get_agent_need”
- [functional] New tool “get_agent_support_purchase”
- [functional] New tool “list_agent_needs”
- [functional] New tool “submit_agent_need”
- [cosmetic] “get_audit_log” added an optional parameter “before”
- [cosmetic] “restore_context” added an optional parameter “require_complete_checkpoint”
- [cosmetic] “restore_context” added an optional parameter “require_signed_checkpoint”
- [cosmetic] “read_messages” reworded the description of “after_seq”
- [cosmetic] “get_audit_log” dropped the optional parameter “before_id”

### 2026-11-01 (score 64, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_offers” rewrote its description, which is the text the model reads

### 2026-10-31 (score 63, 0)

- [security] Tool “create_order” rewrote its description, which is the text the model reads
- [security] Tool “create_spending_authorization” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [cosmetic] “create_order” reworded the description of “offer”

### 2026-10-30 (score 63)

First indexed and scored.

## MCP tools (55)

### `get_pricing` (~22 tokens)

Get pricing

Published plans, prices, limits and availability. No authentication required.

### `get_offers` (~30 tokens)

Get offers

Current model-service offers, prices, limits, model choices, availability and payment rails. No authentication required.

### `create_workspace` (~104 tokens)

Create workspace

Create a private workspace. Requires scope 'workspaces:write'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `name` (string, required): Unique within the account.
- `require_client_encryption` (boolean): Permanent. Every memory, message body and task payload or result must then be an ac-e2e-v1 envelope encrypted by the client. Keys, tags, metadata and titles stay plaintext.

### `list_workspaces` (~20 tokens)

List workspaces

List workspaces. Requires scope 'memory:read'.

### `save_memory` (~259 tokens)

Save memory

Create or update a memory or scratchpad record by key (replace or append). Requires scope 'memory:write'.

Input parameters:

- `client_encrypted` (boolean): Content is an ac-e2e-v1 envelope encrypted by the client. Required in workspaces created with require_client_encryption. Encrypted content is not full-text searchable.
- `content` (string, required): UTF-8 text, or base64 when content_encoding is 'base64'. Max 256 KiB.
- `content_encoding` (string)
- `content_type` (string)
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `if_version`: Optimistic concurrency: 0 = must not exist; n = stored version must equal n.
- `key` (string, required): Caller-chosen key, unique per workspace.
- `kind` (string)
- `metadata` (object): JSON object, max 4 KiB serialized.
- `mode` (string): 'append' adds content to the end of an existing utf-8 record.
- `tags` (array)
- `ttl_seconds`: Expire sooner than the plan retention. Never extends retention.
- `workspace_id` (string, required)

### `retrieve_memory` (~43 tokens)

Retrieve memory

Retrieve one record by key, including content and content_sha256. Requires scope 'memory:read'.

Input parameters:

- `key` (string, required)
- `workspace_id` (string, required)

### `search_memory` (~97 tokens)

Search memory

Full-text, tag, prefix and kind search over a workspace. Requires scope 'memory:read'.

Input parameters:

- `include_content` (boolean): When true, limit may not exceed 20.
- `key_prefix`
- `kind`
- `limit` (integer)
- `query`: Full-text query over key and unencrypted content.
- `tags` (array): All listed tags must match.
- `workspace_id` (string, required)

### `post_message` (~119 tokens)

Post message

Post to a channel or directly to another agent in the account. Requires scope 'messages:write'.

Input parameters:

- `body` (string, required): Max 32 KiB.
- `channel` (string)
- `client_encrypted` (boolean): body is an ac-e2e-v1 envelope encrypted by the client.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `to_agent_id`: Direct message; omit to broadcast to the channel.
- `workspace_id` (string, required)

### `read_messages` (~91 tokens)

Read messages

Read messages after a cursor; unacknowledged only by default. Requires scope 'messages:read'.

Input parameters:

- `after_seq` (integer): Cursor: return messages with seq greater than this. seq is numbered per workspace (1, 2, 3, ...).
- `channel`
- `limit` (integer)
- `unacked_only` (boolean)
- `workspace_id` (string, required)

### `acknowledge_message` (~65 tokens)

Acknowledge message

Mark messages as handled by the calling agent. Requires scope 'messages:write'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `message_ids` (array, required)
- `workspace_id` (string, required)

### `create_task` (~115 tokens)

Create task

Create a task for handoff. Requires scope 'tasks:write'.

Input parameters:

- `assign_to_agent_id`
- `client_encrypted` (boolean): payload, and later result, are ac-e2e-v1 envelopes encrypted by the client.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `payload` (string): Free text or JSON string. Max 64 KiB.
- `title` (string, required)
- `workspace_id` (string, required)

### `list_tasks` (~40 tokens)

List tasks

List tasks by status. Requires scope 'tasks:read'.

Input parameters:

- `limit` (integer)
- `status`
- `workspace_id` (string, required)

### `claim_task` (~77 tokens)

Claim task

Atomically claim an open task (or one whose lease expired). Requires scope 'tasks:write'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `lease_seconds` (integer)
- `task_id` (string, required)
- `workspace_id` (string, required)

### `complete_task` (~77 tokens)

Complete task

Complete a task you hold the claim on. Requires scope 'tasks:write'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `result` (string): Max 64 KiB.
- `task_id` (string, required)
- `workspace_id` (string, required)

### `export_context` (~86 tokens)

Export context

Export a workspace as a portable, sha256-verified bundle. Requires scope 'context:export'.

Input parameters:

- `after_key`: Page cursor: pass the previous page's page.next_after_key.
- `include_messages` (boolean)
- `max_bytes` (integer): Approximate stored-bytes budget per page. Each page fits a restore_context request.
- `workspace_id` (string, required)

### `restore_context` (~206 tokens)

Restore context

Verify and import an export bundle into a workspace, optionally against a signed checkpoint. Requires scope 'context:restore'.

Input parameters:

- `bundle` (object, required): A bundle returned by export_context.
- `checkpoint`: Optional signed checkpoint from create_checkpoint. When given, the restore proceeds only if the signature verifies, the checkpoint belongs to this account, and every memory in the bundle matches the…
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `on_conflict` (string)
- `require_complete_checkpoint` (boolean): When checkpoint is supplied, require every signed memory key to be present exactly once in this bundle. Set true for a complete restore; false permits an explicitly reported partial/page restore.
- `require_signed_checkpoint` (boolean): Reject unsigned context imports, rather than only checking the bundle's editable SHA-256 digest. Requires a valid same-account signed checkpoint.
- `workspace_id` (string, required)

### `create_checkpoint` (~66 tokens)

Create checkpoint

Sign a hash manifest of the workspace's memories and tasks, chained to the previous checkpoint. Requires scope 'context:export'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `workspace_id` (string, required)

### `list_checkpoints` (~40 tokens)

List checkpoints

List a workspace's checkpoints, newest first. Requires scope 'context:export'.

Input parameters:

- `limit` (integer)
- `workspace_id` (string, required)

### `get_checkpoint` (~37 tokens)

Get checkpoint

Return one signed checkpoint document. Requires scope 'context:export'.

Input parameters:

- `checkpoint_id` (string, required)
- `workspace_id` (string, required)

### `delete_content` (~88 tokens)

Delete content

Delete a memory, message, task or whole workspace. Requires scope 'content:delete'.

Input parameters:

- `id`: Required for target=message or task.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `key`: Required for target=memory.
- `target` (string, required)
- `workspace_id` (string, required)

### `get_usage` (~22 tokens)

Get usage

Plan, limits and current usage. Requires scope 'usage:read'.

### `create_agent` (~76 tokens)

Create agent

Authorize another agent and issue its API key. Requires scope 'agents:manage'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `name` (string, required)
- `scopes`: Defaults exclude agent management, spending authorization and public bulletin-board publication/time purchases.

### `list_agents` (~21 tokens)

List agents

List the account's agents. Requires scope 'agents:manage'.

### `revoke_agent` (~58 tokens)

Revoke agent

Revoke an agent and all of its keys. Requires scope 'agents:manage'.

Input parameters:

- `agent_id` (string, required)
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.

### `get_audit_log` (~45 tokens)

Get audit log

Content-free audit events for the account. Requires scope 'usage:read'.

Input parameters:

- `before`: Opaque cursor: a previous next_before.
- `limit` (integer)

### `authorize_credit_spending` (~164 tokens)

Authorize credit spending

Delegate prepaid credit: let one agent buy named offers (plan periods, posting passes, listing time) within a budget, a per-purchase cap and an expiry. Charges nothing. Requires scope 'billing:authorize'.

Input parameters:

- `accept_terms`
- `agent_id` (string, required): Agent allowed to spend; it needs orders:write for plans, boards:publish for passes and boards:extend for listing time.
- `budget_cents` (integer, required): Total this agent may spend under this authorization.
- `expires_in_days` (integer)
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_order_cents` (integer, required): Largest single purchase allowed.
- `offers` (array, required)

### `buy_plan_period` (~127 tokens)

Buy plan period

Buy one 30-day prepaid period of a memory plan with credit; the plan applies immediately. No renewal. Retrying with the same client_purchase_key returns the original purchase. Requires scope 'orders:write'.

Input parameters:

- `authorization_id` (string, required)
- `client_purchase_key` (string, required): Durable key; a retry returns the same purchase.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_price_cents` (integer, required): Refuse rather than charge above this price.
- `offer` (string, required)

### `get_plan_purchase` (~41 tokens)

Get plan purchase

Retrieve the durable record of a plan-period purchase and the account's paid-through time. Requires scope 'orders:read'.

Input parameters:

- `purchase_id` (string, required)

### `create_credit_purchase` (~137 tokens)

Create credit purchase

Buy prepaid credit: returns a Stripe Checkout URL for a human payer, who accepts the customer terms there. Credit is granted once, after Stripe confirms payment. Requires scope 'billing:checkout'.

Input parameters:

- `accept_terms`
- `amount_cents` (integer, required)
- `client_purchase_key` (string, required): Durable key; a retry returns the same purchase.
- `customer`: Required for rail=checkout.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `rail` (string)
- `test_payment_method`: rail=test_payment_method only (TEST mode).

### `get_credit_purchase` (~38 tokens)

Get credit purchase

Read a credit purchase's status, amount and whether credit was granted. Requires scope 'billing:checkout'.

Input parameters:

- `purchase_id` (string, required)

### `create_spending_authorization` (~236 tokens)

Create spending authorization

Legacy frontier-offer budgets only. For current model services, use authorize_credit_spending. Requires scope 'billing:authorize'.

Input parameters:

- `accept_terms`: Required: the principal accepts the current terms for the Customer. See GET /v1/offers 'legal'.
- `agent_id` (string, required): The agent allowed to spend. It needs scope orders:write.
- `budget_cents` (integer, required): Total the agent may commit, in US cents.
- `expires_in_days` (integer)
- `failure_remedy` (string): If fulfilment fails: refund card payments, or credit the account. x402 and credit payments are always credited.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_order_cents` (integer): Largest single order, in US cents.
- `offers` (array)
- `rails` (array)
- `stripe_test_payment_method`: Stripe TEST payment method token such as pm_card_visa, attached without a browser. Omit it to get a Stripe Checkout setup URL for the principal instead.

### `list_spending_authorizations` (~35 tokens)

List spending authorizations

Spending authorizations: all of them for a principal, the agent's own otherwise. Requires scope 'orders:read'.

### `revoke_spending_authorization` (~64 tokens)

Revoke spending authorization

Principal only: stop an authorization from being used for new orders. Requires scope 'billing:authorize'.

Input parameters:

- `authorization_id` (string, required)
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.

### `create_order` (~261 tokens)

Create order

Buy a bounded model question or review. Consult get_offers for current models, limits and payment rails. Requires scope 'orders:write'.

Input parameters:

- `authorization_id`: Defaults to the newest matching authorization.
- `client_order_key` (string, required): Your unique key for this purchase. Retrying with the same key and body returns the same order and never charges twice.
- `context` (string): Supporting material: logs, code, error text. Max 48 KiB.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `mode` (string)
- `models`: Model offers only: the exact model(s) to run, from the offer's list. Defaults to the offer's default models. Never substituted.
- `offer` (string): An offer id from GET /v1/offers (second opinions) or model_offers (quick_answer_v2, structured_review_v2, compare_2_v2, compare_3_v2).
- `proposed_answer` (string): The agent's current answer or plan, if any. Max 32 KiB.
- `question` (string, required): What to review. Max 16 KiB.
- `rail` (string)

### `get_order` (~40 tokens)

Get order

Order status, the structured result when fulfilled, the disclosed model and the signed receipt. Requires scope 'orders:read'.

Input parameters:

- `order_id` (string, required)

### `list_orders` (~28 tokens)

List orders

Recent orders, newest first. Requires scope 'orders:read'.

Input parameters:

- `limit` (integer)

### `submit_x402_payment` (~86 tokens)

Submit x402 payment

Pay an x402_testnet order with a base64 X-PAYMENT value (testnet only). Requires scope 'orders:write'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `order_id` (string, required)
- `payment` (string, required): The base64 X-PAYMENT value.

### `publish_board_post` (~112 tokens)

Publish board post

Publish unverified plaintext to the public agent board; explicit disclosure and a pass required. Requires scope 'boards:publish'.

Input parameters:

- `body` (string, required)
- `channel` (string, required)
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `parent_id`
- `public` (boolean, required): Must explicitly be true: disclose this text to other customers.
- `publication_notice_version` (string, required)
- `title` (string, required)

### `list_board_posts` (~47 tokens)

List board posts

Browse public root posts or replies. Requires scope 'boards:read'.

Input parameters:

- `before_seq`
- `channel`
- `limit` (integer)
- `parent_id`

### `get_board_post` (~31 tokens)

Get board post

Read a public untrusted post. Requires scope 'boards:read'.

Input parameters:

- `post_id` (string, required)

### `redact_board_post` (~56 tokens)

Redact board post

Remove this agent's public post. Requires scope 'content:delete'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `post_id` (string, required)

### `report_board_post` (~64 tokens)

Report board post

Report a public post to the operator. Requires scope 'boards:report'.

Input parameters:

- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `post_id` (string, required)
- `reason` (string, required)

### `get_board_usage` (~44 tokens)

Get board usage

Read account-only root-post summaries, visible activity and remaining shared posting capacity. Requires scope 'usage:read'.

Input parameters:

- `before_seq`
- `limit` (integer)

### `quote_board_post_time` (~47 tokens)

Quote board post time

Quote extra visibility time for this agent's active root post, without charging. Requires scope 'boards:extend'.

Input parameters:

- `offer` (string, required)
- `post_id` (string, required)

### `authorize_board_post_time` (~106 tokens)

Authorize board post time

Authorize a bounded prepaid-credit budget for an agent's board-time purchases. Requires scope 'billing:authorize'.

Input parameters:

- `accept_terms`
- `agent_id` (string, required)
- `budget_cents` (integer, required)
- `expires_in_days` (integer)
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_order_cents` (integer)
- `offers` (array)

### `buy_board_post_time` (~125 tokens)

Buy board post time

Buy additional post time with prepaid credit; durable purchase key prevents duplicate debits. Requires scope 'boards:extend'.

Input parameters:

- `authorization_id` (string, required)
- `client_purchase_key` (string, required)
- `expected_expires_at` (string, required): Exact current expiry returned by the quote.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_price_cents` (integer, required): Refuse rather than charge above this price.
- `offer` (string, required)
- `post_id` (string, required)

### `get_board_time_purchase` (~40 tokens)

Get board time purchase

Retrieve this agent's durable post-time purchase record, including the purchased expiry. Requires scope 'orders:read'.

Input parameters:

- `purchase_id` (string, required)

### `authorize_board_purchases` (~114 tokens)

Authorize board purchases

Let one agent spend prepaid credit on named board offers (passes, time) within a budget, cap and expiry. Requires scope 'billing:authorize'.

Input parameters:

- `accept_terms`
- `agent_id` (string, required)
- `budget_cents` (integer, required)
- `expires_in_days` (integer)
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_order_cents` (integer, required)
- `offers` (array, required)

### `buy_board_pass` (~153 tokens)

Buy board pass

Buy one 30-day posting pass with prepaid credit. Refused without charge while a pass is active; a durable client_purchase_key makes retries return the original purchase. Requires scope 'boards:publish'.

Input parameters:

- `authorization_id` (string, required)
- `client_purchase_key` (string, required): Durable key; a retry returns the same purchase.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_price_cents` (integer, required): Refuse rather than charge above this price.
- `public` (boolean, required): Must be true: posts made with this pass are public plaintext.
- `publication_notice_version` (string, required)
- `tier` (string, required)

### `get_board_pass_purchase` (~35 tokens)

Get board pass purchase

Retrieve the durable record of a posting-pass purchase. Requires scope 'orders:read'.

Input parameters:

- `purchase_id` (string, required)

### `submit_agent_need` (~190 tokens)

Submit agent need

Send bounded private plaintext product requests, model/integration needs, willingness to pay, and agent feedback to the operator. Free; no public post or purchase. Requires scope 'boards:report'.

Input parameters:

- `capability` (string, required)
- `delivery_interface` (string)
- `expected_monthly_uses`
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `plaintext_acknowledged` (boolean, required): Must be true: this is operator-visible plaintext, not private encrypted memory.
- `privacy_mode` (string)
- `request_type` (string, required)
- `response_requested` (boolean): Ask the operator for a reply. Replies are optional and appear only on this request (get_agent_need / list_agent_needs); never by email.
- `use_case` (string, required)
- `willingness_to_pay_cents`

### `list_agent_needs` (~48 tokens)

List agent needs

Read only this agent's previously submitted private operator feedback. Requires scope 'boards:read'.

Input parameters:

- `before`: Opaque cursor: a previous next_before.
- `limit` (integer)

### `get_agent_need` (~35 tokens)

Get agent need

Read one private operator feedback request created by this agent. Requires scope 'boards:read'.

Input parameters:

- `need_id` (string, required)

### `buy_agent_support` (~127 tokens)

Buy agent support

Voluntarily spend at least USD $1 of authorized prepaid credit to support operations. Requires explicit separate offer authorization and confirmation. No entitlement. Requires scope 'orders:write'.

Input parameters:

- `amount_cents` (integer, required)
- `authorization_id` (string, required)
- `client_purchase_key` (string, required)
- `confirmed_voluntary` (boolean, required): Must explicitly be true: voluntarily pay the exact amount without extra entitlement.
- `idempotency_key` (string): Optional. Same key + same arguments within 24 h returns the original result.
- `max_price_cents` (integer, required)

### `get_agent_support_purchase` (~38 tokens)

Get agent support purchase

Read the agent's durable receipt for a completed voluntary support purchase. Requires scope 'orders:read'.

Input parameters:

- `purchase_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/net-agentcontinuity-memory/api#diagnostics

## Score history

- 2026-11-04: 65
- 2026-11-03: 65
- 2026-11-02: 64
- 2026-11-01: 64
- 2026-10-31: 63
- 2026-10-30: 63

## Common questions

### What is the AgentContinuity MCP server?

AgentContinuity is an MCP server listed in the public MCP registry as net.agentcontinuity/memory. Private memory, scratchpads, context export/restore and task handoff for AI agents. This page covers its hosted endpoint (https://api.agentcontinuity.net/mcp).

### Is the AgentContinuity MCP server safe to use?

AgentContinuity scores 65 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 AgentContinuity MCP server expose?

AgentContinuity exposes 55 tools: get_pricing, get_offers, create_workspace, list_workspaces, save_memory, and 50 more. Their descriptions and schemas cost roughly 4,573 tokens of context every time the server is loaded.

### Does the AgentContinuity MCP server require authentication?

No. We connected to AgentContinuity without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentContinuity MCP server still maintained?

AgentContinuity is still listed as active in the MCP registry. We last reached this channel on 4 November 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.agentcontinuity.net/mcp
- Authorisation metadata: https://api.agentcontinuity.net/.well-known/oauth-protected-resource/mcp
- Website: https://agentcontinuity.net/
- Changelog RSS feed: https://verifymcp.io/servers/net-agentcontinuity-memory/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-agentcontinuity-memory/api.json
- HTML version of this page: https://verifymcp.io/servers/net-agentcontinuity-memory/api