Skip to main content
Glama

Server Details

Train a text classifier from your labelled examples in a minute; label texts with probabilities.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 6 tools

Disambiguation4/5

Each tool maps to a distinct action+resource: create/train, predict, get one classifier, list classifiers, service info, and agent registration. The only mild overlap is between get_decide_classifier (one classifier's status) and get_decide_info (plan/limits/benchmarks), but the descriptions make the boundary clear.

Naming Consistency4/5

All names follow snake_case verb_noun form, which is readable and predictable. However, the 'decide' token floats inconsistently (prefix in decide_create_classifier/decide_predict, infix in get_decide_classifier/list_decide_classifiers), and register_agent drops the domain prefix entirely.

Tool Count5/5

Six tools is well-scoped for a text-classification service: train, predict, inspect, list, learn about the service, and authenticate. No tool looks redundant or bolted on.

Completeness3/5

Core lifecycle of train → poll status → predict → list is covered, but there is no delete/remove classifier and no way to update examples, retrain, or tune the confidence threshold. The missing delete is notable given plan limits (Free allows only 1 classifier), leaving agents without a way to clean up failed or stale classifiers.

Available Tools

6 tools
decide_create_classifierDecide Create ClassifierAInspect

Tuatara Decide: train a text classifier from labelled examples (at least 2 per label, up to 255 labels). Training takes about a minute for small sets and draws on the account's NEXUS plan; the Free plan allows 1 classifier.

Inputs: name (required), examples (required), threshold, instructions.

decide_predictDecide PredictAInspect

Tuatara Decide: label up to 256 texts with a ready classifier. Each result has the label, its confidence, every label's probability and unsure=true when confidence is under the classifier's threshold. Each text counts as one decision on the account's plan.

Inputs: classifier_id (required), text, texts.

get_decide_classifierGet Decide ClassifierA
Read-onlyIdempotent
Inspect

Tuatara Decide: one classifier's status (queued / training / ready / failed), labels and expected accuracy on held-out examples. Poll this after creating one.

Inputs: classifier_id (required).

get_decide_infoGet Decide InfoB
Read-onlyIdempotent
Inspect

Tuatara Decide: what it is, the NEXUS plan allowances (classifiers and decisions a week), limits and the public benchmark evidence. Read-only, no auth.

Inputs: no named parameters.

list_decide_classifiersList Decide ClassifiersC
Read-onlyIdempotent
Inspect

Tuatara Decide: your classifiers, your plan and its classifier limit and weekly decisions.

Inputs: no named parameters.

register_agentRegister AgentAInspect

Register this agent and get its API key — the same as POST https://cymetica.com/mcp/v1/register, no key needed. Returns api_key (shown once) and agent_id. Then either set it as the X-API-Key (or Authorization: Bearer) header of this connection, or pass it as "api_key" in the arguments of any later tool call — e.g. get_deposit_address {"api_key": ""}.

Inputs: name (required), intended_use (required), contact_email (required), via.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients to make typed, single-pass decisions over text—choosing among options, answering yes/no checks, scoring on a defined ordinal scale, or asking multiple questions about the same text—with probabilities returned for each result. It runs the model locally on CPU and supports stdio and Streamable HTTP transports.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to obtain calibrated probabilities, option picks, scale scores, and multi-question judgments for batches of short text, returning numeric results for sorting, filtering, and counting.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources