Gnosari MCP

Manage Data Collection

gnosari_manage_data_collection

Create, list, get, update, delete, assign, or remove data collection templates.

Templates define what structured data agents extract from conversations. Also controls whether visitors can upload files (photos/PDFs) for the agent to read — pass enable_attachments (requires gnosari_id).

Assigning a template (action='assign', or create with gnosari_id) turns data collection ON for that agent. Removing a template never turns it off — the enable state is the owner's setting, changed only through the agent's own configuration.

Identity: pass identity_field (create/update) to name the field that holds the person's display name. On update, omitted fields are preserved (preserve-on-omit); to drop the designation pass clear_fields=["identity_field"] — never an empty string. Listing a field in clear_fields AND passing it as a value is rejected.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Template name (create/update)
`action`	Yes	Action to perform on data collection templates
`fields`	No	Template fields (create/update)
`search`	No	Search query (list)
`gnosari_id`	No	Agent ID (assign/remove, or create+assign). Also required when setting enable_attachments.
`description`	No	Template description (create/update)
`template_id`	No	Template ID (get/update/delete/assign/remove)
`clear_fields`	No	Fields to reset to their default (NULL) on update. Currently supports 'identity_field' — clearing it drops the identity designation and reverts to server heuristic resolution. Passing a field here AND as a value param is an error.
`custom_prompt`	No	Custom collection flow prompt. Required when collection_mode='guided'; ignored otherwise
`identity_field`	No	Name of the field to use as the person's identity/display name (create/update). Must name one of this template's fields. Server-side identity resolution uses it to compute display_name on collected records. On update, omit to leave unchanged; to remove the designation pass 'identity_field' in clear_fields (never an empty string).
`include_system`	No	Include system templates (list)
`collection_mode`	No	How the agent collects data. passive: Extract only what users volunteer. Never asks. opportunistic: Extract + nudge when contextually natural. active: Proactively ask for missing required fields until complete. Default for intake/forms agents — use unless you have a reason not to. guided: Fully custom flow driven by custom_prompt (required). Rarely needed — the other modes cover almost every case.
`enable_attachments`	No	Turn file uploads on/off for this agent's chat (per-agent capability, requires gnosari_id). true = visitors can attach a photo or PDF and the agent reads it and extracts the data you collect — recommended when the agent collects data users would otherwise type or send separately. false = uploads off. null (default) = leave unchanged. Ask the user whether they want visitors to be able to upload documents before setting this.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 13, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond annotations: discloses preserve-on-omit on update, that removing never disables collection, that identity_field must name one of the template's fields, and that identity_field cannot be set alongside clear_fields. These are non-obvious behavioral rules an agent needs to call correctly.

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

Conciseness4/5

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

Front-loads the action list then explains templates and their semantics. A few sentences are long, but each carries distinct information. Slightly dense but no clear filler.

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

Completeness5/5

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

With 13 parameters, an output schema, and no nested objects, the description covers all the non-obvious behaviors (preserve-on-omit, assign vs remove, identity field handling) that the schema alone doesn't convey. Very complete.

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

Parameters5/5

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

Schema coverage is 100% so baseline is 3, but the description adds real meaning: the assign semantics of gnosari_id, the identity_field/clear_fields interaction rule, and the required-gnosari_id constraint for enable_attachments. This goes beyond restating schema.

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

Purpose4/5

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

States a specific verb set (create, list, get, update, delete, assign, remove) and resource (data collection templates), and explains what templates do. Sibling tools like gnosari_manage_knowledge and gnosari_manage_traits are in the same family but the description doesn't explicitly distinguish itself from them.

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?

Provides clear context: assign turns collection ON, remove never turns it off, and the enable state is owner-controlled. Explains the clear_fields vs value-param error condition. Does not name alternative tools explicitly, but the when-to-use semantics are well-covered.

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

All Gnosari MCP 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?