Marcora

create_context_collection

Create a new context collection to organize your reference materials. Collections group related context items together for easier management and targeted retrieval.

Parameters:
- name: A descriptive name for the collection (e.g., "Brand Guidelines", "Product Research Q2")
- description: A short description of what this collection contains
- is_private: If true, only you can see this collection. If false, all team members can access it.

After creating a collection, use the returned 'id' with the add_context tool (pass it as collection_id) to add context items to this collection. You can also use list_context_collections to see all existing collections and their IDs.

The response includes a link_url that opens the new collection directly in the Marcora web app.

**Links:** present `link_url` to the user exactly as returned — copy it character for character. Never retype, shorten, or rebuild a link or the IDs inside it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "description": "<description>",
      "is_private": "<is_private>"
    },
    "name": "create_context_collection"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Display name for the collection, shown wherever collections are listed and picked. Required. Make it specific — "Q2 Product Research" rather than "Research" — since it is the only label anyone sees when filing reference material into it.
`is_private`	Yes	true makes the collection visible only to you: material filed in it is hidden from every other team member, including from their list_context_items and get_context_item calls. false shares it with the whole team, which is the default and the right choice unless the user explicitly asks to keep it to themselves.
`description`	Yes	Free-text note on what belongs in this collection, so you and teammates file material consistently later. It is stored for display only and has no effect on search, retrieval, or generation. An empty string is accepted if there is nothing useful to say.

Output Schema

Name	Required	Description
`id`	No	Collection ID. Pass this as collection_id to add_context to add items to this collection.
`name`	No	Collection name.
`link_url`	No	URL to view this collection in the Marcora web app.
`created_at`	No	Unix timestamp of creation.
`is_private`	No	Whether this collection is private to the creator.
`description`	No	Collection description.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: the privacy semantics (is_private=true hides items from teammates' list_context_items and get_context_item results) and the presence of a link_url in the response. It doesn't spell out that repeated calls with the same name create distinct collections, but the idempotentHint already signals that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening purpose sentence and the workflow/link guidance are well front-loaded and earn their place, but the middle "Parameters" block duplicates schema content at lower fidelity, adding bulk without new information. The bolded link-handling instruction is useful but lengthy relative to the rest.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't document return values, yet it still flags link_url and mandates exact copying — helpful for a creation tool that hands off to add_context. Annotations cover safety, so the remaining coverage is adequate; it could be stronger only by warning about duplicate collection names.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema descriptions are substantially richer than the description's parameter list (e.g., the schema explains that description has no effect on search/retrieval and that is_private is team-visible by default). The description's restatement adds no meaning beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ("Create a new context collection") plus its organizational purpose, and implicitly distinguishes it from siblings like add_context and list_context_collections by naming both and describing how they relate. An agent can immediately tell this is the creation step of a collection workflow.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent what to do next (use the returned 'id' with add_context as collection_id) and points to list_context_collections for existing collections. It does not explicitly say when NOT to use it (e.g., check for an existing collection first to avoid duplicates), so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Marcora tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?