Agent Context Manager by Apoth3osis

Name: Agent Context Manager
Brand: Apoth3osis
SKU: 6a389fd44cde57baf7edba1b
Availability: InStock

Agent Context Manager

Core Utility

Available ActionsEach successful request consumes credits as outlined below.

listfetchcreateupdaterequest_unlockarchiveclone_templateversions

Details

Give your AI agents a single source of truth. Agent Context Manager lets you create, organize, version, and reuse the knowledge your agents and workflows rely on -- brand guidelines, standard operating procedures, product and pricing facts, tone-of-voice rules, and domain expertise -- so every agent acts on the same up-to-date information. Start from polished public templates, clone them into your private library, and edit once: every agent and workflow that references a document stays in sync automatically. Built-in version history shows exactly what changed, who changed it, and lets you roll back with confidence.

Use Cases

Define a brand voice and style guide once and have every content agent follow it. Store standard operating procedures so support and operations agents handle tasks consistently. Keep product catalogs, pricing rules, and policy documents in one place that workflows reference at runtime. Onboard a new agent instantly by attaching a curated set of context documents instead of rewriting prompts. Roll out a company-wide change by editing a single document instead of updating every workflow that uses it. Clone a vetted public template -- such as a customer-support playbook or editorial style guide -- and tailor it to your business. Audit and roll back changes to mission-critical instructions using full version history.

Dynamic MCP Setup

Connect once through AgentPMT Dynamic MCP, then use approved tools from the same agent connection.

30 Second Setup

STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections.

npm install -g @agentpmt/mcp-routeragentpmt-setup

Hosted Streamable HTTPS

MCP endpoint for browser-based apps like ChatGPT, Claude, Grok, or any time you want a streamable connection with no local install.

https://api.agentpmt.com/mcp

Config Example

Use the hosted endpoint directly in clients that support remote MCP. Store your Bearer token in the client config or secret field.

Full connection guide

{
  "mcpServers": {
    "agentpmt": {
      "type": "streamable-http",
      "url": "https://api.agentpmt.com/mcp",
      "headers": {
        "Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
        "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
      }
    }
  }
}

Need client videos, organization controls, audit details, and the full feature overview?

More About Dynamic MCP

Actions(8)

list4 params

List readable Agent Context documents.

querystring

Optional search over title, summary, and tags for list.

scopestring

List scope. Use all to include owned private documents and public templates.

Values:

privatepublic_templateall

Default: private

include_archivedboolean

When true, include archived documents in list results.

limitinteger

Maximum documents to return for list.

Default: 100

Range: 1 - 200

fetch1 param(1 required)

Fetch one readable Agent Context document.

context_document_idrequiredstring

Agent Context document ObjectId. Required for fetch/update/archive/clone_template/versions.

create6 params(2 required)

Create an Agent Context document.

titlerequiredstring

Document title for create/update.

bodyrequiredstring

Document body for create/update.

summarystring

Optional short summary for create/update.

tagsarray

Optional tags for create/update.

Array of: string

document_scopestring

Create-only scope. public_template requires admin JWT.

Values:

privatepublic_template

Default: private

agent_edit_approval_requiredboolean

When true, agents need a user-approved temporary unlock before editing this document.

update6 params(1 required)

Update editable fields on an Agent Context document.

context_document_idrequiredstring

Agent Context document ObjectId. Required for fetch/update/archive/clone_template/versions.

titlestring

Document title for create/update.

summarystring

Optional short summary for create/update.

bodystring

Document body for create/update.

tagsarray

Optional tags for create/update.

Array of: string

agent_edit_approval_requiredboolean

When true, agents need a user-approved temporary unlock before editing this document.

request_unlock1 param(1 required)

Request a temporary 30-minute edit unlock for a locked Agent Context document.

context_document_idrequiredstring

Agent Context document ObjectId. Required for fetch/update/archive/clone_template/versions.

archive1 param(1 required)

Archive an Agent Context document.

context_document_idrequiredstring

Agent Context document ObjectId. Required for fetch/update/archive/clone_template/versions.

clone_template1 param(1 required)

Clone a public Agent Context template into private context.

context_document_idrequiredstring

Agent Context document ObjectId. Required for fetch/update/archive/clone_template/versions.

versions1 param(1 required)

List retained versions for a readable Agent Context document.

context_document_idrequiredstring

Agent Context document ObjectId. Required for fetch/update/archive/clone_template/versions.

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "6a389fd44cde57baf7edba1b",
    "parameters": {
      "action": "list",
      "scope": "private",
      "limit": 100
    }
  }'

import requests
import json

url = "https://api.agentpmt.com/products/purchase"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer ********"
}

data = {
    "product_id": "6a389fd44cde57baf7edba1b",
    "parameters": {
        "action": "list",
        "scope": "private",
        "limit": 100
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.status_code)
print(response.json())

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "6a389fd44cde57baf7edba1b",
  parameters: {
    "action": "list",
    "scope": "private",
    "limit": 100
  }
};

fetch(url, {
  method: "POST",
  headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error("Error:", error));

const axios = require('axios');

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "6a389fd44cde57baf7edba1b",
  parameters: {
    "action": "list",
    "scope": "private",
    "limit": 100
  }
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error("Error:", error.message);
  });

Login to view your API and budget keys. The example above uses placeholder values. Sign in to see personalized code with your bearer token.

Autonomous agents can access this tool through AgentAddress credit balances or direct x402 payments. Use the Autonomous Agent API reference for endpoint shapes after choosing the access pattern below.

Recommended

Credit-Based Access Using AgentAddress

AgentAddress is preferred when an autonomous agent needs persistent file access, stored platform state, or maximum tool use ability across repeated calls.

Open Credit-Based Access Using AgentAddress

Direct x402 Payment

Use direct x402 for independent one-off tool calls that do not require shared files or stored platform state.

Accepted public payments

Stablecoin: USDC
Chains: Base, Arbitrum, Optimism, Polygon, and Avalanche

Direct x402 payments are not enabled for this product; use AgentAddress credit access instead.

Product Skill Package

This product has a published Agent Skill package. Install it when an autonomous agent needs product-specific operating instructions in its local skill registry.

Download SKILL.md View package source OpenClaw listing

OpenClaw install

Copied to clipboard

skills.sh install

Copied to clipboard

Usage Instructions

Usage guidance provided directly by the developer for this product.

Agent Context Manager

Agent Context Manager stores and maintains reusable Agent Context documents -- the persistent knowledge your AI agents and workflows draw on every time they run (brand guidelines, SOPs, product facts, tone rules, domain expertise). Maintain a document once and every agent or workflow that references it stays in sync.

Document fields

title (required) -- short, descriptive name.
summary (optional) -- one-line overview shown in lists and pickers.
body (required) -- the full knowledge the agent should load. Markdown is supported.
tags (optional) -- keywords for search and organization.
scope -- private (yours to create and edit) or public_template (admin-managed, available for anyone to clone).

Actions

list -- list and search readable documents. Use scope: private (default), public_template, or all. Supports query, include_archived, and limit.
fetch -- retrieve one document's full body by context_document_id.
create -- create a private document (title and body required). Creating a public_template requires admin access.
update -- edit title, summary, body, or tags on a document you own.
archive -- retire a document so it can no longer be attached, while keeping its history.
clone_template -- copy a public template into your private library so you can customize it. The clone tracks the template it came from.
versions -- review retained revisions (who changed what and when) so you can compare and roll back.

Permissions

Any authenticated user can run every action.
You can only modify your own private documents.
Only admins create or edit public templates.

Best practices

Keep each document focused on one topic (one for brand voice, one for return policy) so agents load only what they need.
Start from a public template when one fits, then clone and tailor it.
Edit the shared document rather than duplicating knowledge across workflows -- one update propagates everywhere.
Use clear titles and tags so documents are easy to find and attach.
Rely on version history before large edits; you can always roll back.

About this Product

Agent Context Manager

AI agents are only as good as the context they are given. Agent Context Manager is the system of record for that context -- a place to write, organize, version, and reuse the knowledge your agents and workflows depend on. Instead of pasting the same instructions into every agent and re-explaining your brand, your policies, and your product details over and over, you maintain them once as reusable Agent Context documents and reference them everywhere.

What is an Agent Context document?

An Agent Context document is a structured, reusable piece of knowledge that agents and workflows load at runtime. Each document has a title, an optional summary, a body (your actual content, written in Markdown), and tags for organization. Typical documents include brand voice and style guides, standard operating procedures, product catalogs and pricing rules, compliance and policy language, and domain expertise that your agents need to act correctly.

Private documents and public templates

Documents come in two scopes. Private documents belong to you -- you create and edit them, and only you can change them. Public templates are admin-curated starting points anyone can clone. When you clone a template, you get a private copy to customize while a link back to the original is preserved for reference.

Write once, stay in sync everywhere

The same document can be attached to many agents and many workflows. Because they all reference the source document, editing it once updates every place that uses it. Roll out a new policy, a tone change, or a product update by editing a single document instead of hunting through every workflow.

Full version history

Every change is tracked. Version history shows what changed, which fields were edited, and when -- so you can review the evolution of a critical instruction and roll back with confidence if an edit does not land the way you expected.

Key capabilities

Create and update private context documents with Markdown bodies.
Browse and search a library of public templates, then clone the ones you want.
List and search your documents by title, summary, and tags.
Archive documents you no longer use while keeping their history.
Review retained versions and roll back changes.

Who it is for

Marketing and content teams enforcing a consistent brand voice, operations and support teams standardizing how agents handle tasks, and anyone building multi-agent systems who needs a reliable, central source of truth for the knowledge their agents act on.

Frequently Asked Questions

How do I connect this tool to an external agent?

You can install the local MCP server by opening a terminal and running:

Install commands

npm install -g @agentpmt/mcp-router
agentpmt-setup

This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc.

Alternatively you can connect to the hosted version with this config block, no installation required:

Hosted MCP config

{
  "mcpServers": {
    "agentpmt": {
      "type": "streamable-http",
      "url": "https://api.agentpmt.com/mcp",
      "headers": {
        "Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
        "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
      }
    }
  }
}

View MCP Connection Instructions for more details.

How does an external agent use this tool?

After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent:

Agent prompt

Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get_instructions' so you know how to use the tool search interface. Then call action 'get_schema' with tool_id 6a389fd44cde57baf7edba1b ("Agent Context Manager"). After reading the schema and any returned instructions, tell me what this tool can do, we are going to be using it

The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT.

Can I reuse one document across multiple agents and workflows?

Yes. That is the point. Attach the same document anywhere it is needed, and edit it once to update every agent and workflow that references it -- no more updating the same instructions in many places.

Does it keep version history and can I roll back?

Yes. Every change is recorded with the fields that changed and when. You can review retained revisions and roll back to an earlier version if an edit does not work out.

How do my agents and workflows actually use these documents?

You attach a document to an agent or workflow, and its content is provided to the agent as context when it runs. Because agents reference the source document, you maintain the knowledge in one place rather than copying it into every prompt.

How is this different from writing instructions directly into each agent's prompt?

Inline prompt instructions are duplicated and drift out of sync across agents. Agent Context documents are a single source of truth: one edit propagates to everything that references the document, and every change is versioned and reversible.

What is an Agent Context document?

It is a reusable, structured piece of knowledge -- a title, optional summary, a Markdown body, and tags -- that your AI agents and workflows load at runtime. Common examples are brand voice guides, standard operating procedures, product and pricing facts, and policy or compliance language.

What is the difference between a private document and a public template?

Private documents are yours -- you create and edit them, and only you can modify them. Public templates are admin-curated starting points that anyone can clone into their private library and then customize.

Who can see or edit my context documents?

You can only modify your own private documents. Any authenticated user can run every action of the tool, but private documents stay under their owner's control, and only admins manage the shared public templates.