Skip to main content
Glama

ThinkNEO Control Plane

Server Details

Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
thinkneo-ai/mcp-server
GitHub Stars
3
Server Listing
ThinkNEO MCP Server

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 3.9/5 across 71 of 71 tools scored. Lowest: 2.9/5.

Server CoherenceA
Disambiguation4/5

Most tools have distinct purposes, but some overlap exists among safety/security tools (check, detect_injection, evaluate_guardrail) and policy tools (check_policy, policy_evaluate). Descriptions help differentiate, but the sheer number of tools (71) increases the chance of misselection.

Naming Consistency5/5

All tools follow a consistent snake_case pattern, with a clear prefix (thinkneo_). The majority use verb_noun structure, and deviations (e.g., decision_cost) are rare and still intuitive. The naming is highly predictable.

Tool Count3/5

71 tools is high, but the server covers a broad domain (governance, observability, registry, etc.). Many tools are granular (e.g., multiple get_* and check_* variants), which could be consolidated. The count is borderline excessive but not unjustified.

Completeness5/5

The tool set comprehensively covers AI governance, observability, security, cost management, performance, verification, and marketplace interactions. No obvious gaps for its stated purpose; all major lifecycle operations are present.

Available Tools

68 tools
thinkneo_a2a_audit
Read-onlyIdempotent
Inspect

Retrieve immutable audit trail for A2A interactions with hash verification. Each event is cryptographically chained for tamper detection.

ParametersJSON Schema
NameRequiredDescriptionDefault
trace_idNoFilter by trace ID
workspaceNoWorkspace identifierdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_a2a_flow
Read-onlyIdempotent
Inspect

Visualize agent-to-agent communication flow. Shows registered agents, their approval status, and interaction patterns from the live gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault
workspaceNoWorkspace identifierdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_a2a_log
Read-onlyIdempotent
Inspect

Retrieve A2A (agent-to-agent) interaction logs from the live gateway. Shows which agents called which, actions performed, costs, and outcomes.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMax events to return
workspaceNoWorkspace identifierdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_a2a_policy
Read-onlyIdempotent
Inspect

Retrieve A2A interaction policies from the live gateway. Shows allowed actions, rate limits, cost caps, and approval requirements.

ParametersJSON Schema
NameRequiredDescriptionDefault
workspaceNoWorkspace identifierdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_agent_roi
Read-onlyIdempotent
Inspect

Calculate ROI per AI agent. Shows value generated vs AI cost consumed, with daily trend, success rate, and comparison to pre-AI baseline. Answers: 'Is this agent generating or consuming value?' and 'What's the ROI trend?'

ParametersJSON Schema
NameRequiredDescriptionDefault
daysNoNumber of days to analyze
workspaceNoWorkspace identifierdefault
agent_nameNoSpecific agent to analyze. If omitted, returns all agents.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_alert_rule_createInspect

Create a Monitor Agent alert rule. Example: notify by email when API key 'X' reaches 75% of its budget → metric=key_spend_pct_of_budget, operator=gte, threshold=75, scope_value=, budget_usd=. Requires an admin API key.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesHuman-readable rule name
metricYesOne of: key_spend_24h_usd, key_spend_30d_usd, key_spend_pct_of_budget, workspace_error_rate_pct, workspace_max_rps, workspace_requests, workspace_spend_24h_usd, workspace_spend_30d_usd
channelsNoComma-separated: email, discord_webhook, whatsappemail
operatorNoComparison: gte, gt, lte, lt, eqgte
severityNolow, medium, high, criticalmedium
thresholdYesThreshold value to compare the metric against
workspaceNoWorkspace id (optional — defaults to the API key's workspace)
budget_usdNoKey budget in USD — required for key_spend_pct_of_budget
scope_valueNoAPI key id — required for key_* metrics
cooldown_minutesNoMinimum minutes between firings

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_alert_rule_delete
DestructiveIdempotent
Inspect

Delete a Monitor Agent alert rule by its rule_id. Requires an admin API key.

ParametersJSON Schema
NameRequiredDescriptionDefault
rule_idYesThe rule_id to delete (from thinkneo_alert_rule_list)
workspaceNoWorkspace id (optional — defaults to the API key's workspace)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_alert_rule_list
Read-onlyIdempotent
Inspect

List your configurable Monitor Agent alert rules. Each rule watches a metric (e.g. an API key reaching a % of its budget, workspace spend, error rate) and notifies your channels (email/discord/whatsapp) when it fires. Requires an admin API key.

ParametersJSON Schema
NameRequiredDescriptionDefault
workspaceNoWorkspace id (optional — defaults to the API key's workspace)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_alert_rule_testInspect

Send a test notification through a rule's configured channels to confirm delivery (email/discord/whatsapp). Requires an admin API key.

ParametersJSON Schema
NameRequiredDescriptionDefault
rule_idYesThe rule_id to test (from thinkneo_alert_rule_list)
workspaceNoWorkspace id (optional — defaults to the API key's workspace)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_audit_export
Read-onlyIdempotent
Inspect

Export audit events from the live gateway. Supports JSON and CSV formats with date range filtering for SIEM integration.

ParametersJSON Schema
NameRequiredDescriptionDefault
formatNoOutput format: ndjson or csvndjson
end_dateNoEnd date ISO format
workspaceNoWorkspace identifierdefault
start_dateNoStart date ISO format

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_benchmark_compare
Read-onlyIdempotent
Inspect

Compare providers side-by-side for a specific task type. Shows quality scores, verification rates, and rankings based on real outcomes. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
providersNoOptional list of providers to compare (e.g., ['anthropic', 'openai']). Leave empty for all.
task_typeYesTask type to compare: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_benchmark_report
Read-onlyIdempotent
Inspect

View the outcome benchmark matrix — real quality scores per provider/model/task_type based on verified outcomes, not static estimates. Shows verification rates, sample counts, and rankings. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
task_typeNoFilter by task type: 'summarization', 'code_generation', 'classification', 'translation', etc. Leave empty for all.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_bridge_a2a_to_mcp
Read-onlyIdempotent
Inspect

Bridge A2A agents to MCP tool format.

ParametersJSON Schema
NameRequiredDescriptionDefault
agent_nameNoA2A agent name to map

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_bridge_generate_agent_card
Read-onlyIdempotent
Inspect

Generate an A2A Agent Card from registry data.

ParametersJSON Schema
NameRequiredDescriptionDefault
agent_idYesAgent ID from registry

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_bridge_list_mappings
Read-onlyIdempotent
Inspect

List all MCP <-> A2A bridge mappings for a tenant.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_bridge_mcp_to_a2a
Read-onlyIdempotent
Inspect

Bridge MCP tool registry to A2A format. Shows tool-to-skill mappings.

ParametersJSON Schema
NameRequiredDescriptionDefault
tool_nameNoMCP tool name to bridge

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_business_impact
Read-onlyIdempotent
Inspect

Executive business impact dashboard. Returns a single view of: total value generated by AI agents, total AI cost, net ROI, risk avoided in dollars, cost per decision, top performing agents, and risk event summary. This is the report a CxO needs to justify AI investment.

ParametersJSON Schema
NameRequiredDescriptionDefault
periodNoTime period: 'this-week', 'this-month', 'this-quarter', 'all'this-month
workspaceNoWorkspace identifierdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_cache_status
Read-onlyIdempotent
Inspect

Get semantic cache stats from the live gateway runtime metrics.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_check
Read-onlyIdempotent
Inspect

Free-tier prompt safety check. Analyzes text for prompt injection patterns and PII (credit card numbers, Brazilian CPF, US SSN, email, phone, passwords). Returns a safety assessment with specific warnings. No authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesThe text or prompt to check for safety issues (max 50,000 characters)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_check_pii_international
Read-onlyIdempotent
Inspect

Detect international PII across 30+ document types from 15+ countries: Brazil (CPF, CNPJ, RG, PIS), USA (SSN, EIN, ITIN, Passport), UK (NINO, UTR), Canada (SIN), EU (IBAN, VAT), Germany (Tax-ID), France (INSEE), Spain (DNI/NIE), Italy (Codice Fiscale), Argentina (CUIT), Mexico (CURP/RFC), Australia (TFN/ABN), India (Aadhaar/PAN), China (ID), Japan (My Number), and credit cards (Luhn validated). Required for LGPD/GDPR/HIPAA compliance. No authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesText to scan for PII (max 100,000 chars)
countriesNoFilter by country codes (BR, US, UK, CA, EU, DE, FR, ES, IT, AR, MX, AU, IN, CN, JP, INTL). Empty = all.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_check_policy
Read-onlyIdempotent
Inspect

Check AI governance policies including model access, budget limits, data controls, and agent governance from the ThinkNEO gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault
workspaceNoWorkspace name or IDdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_check_spend
Read-onlyIdempotent
Inspect

Check AI spend summary for a workspace, team, or project. Returns real cost breakdown by provider, model, and time period from the ThinkNEO AI gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault
periodNoTime period: today, this-week, this-month, last-monththis-month
group_byNoGroup costs by: provider, model, team, or projectprovider
workspaceNoWorkspace name or IDdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_compare_models
Read-onlyIdempotent
Inspect

Compare available AI models from the live gateway catalog.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelsYesComma-separated model IDs to compare (e.g. gpt-4o,claude-sonnet-4-20250514,gemini-2.5-flash)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_completeInspect

Run a governed LLM completion through the ThinkNEO AI gateway. The request is authorized, classified, and policy-checked against your workspace governance BEFORE any provider is called — a blocked prompt never reaches the model. Tenant/workspace are derived from your API key.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoprovider/model, e.g. 'anthropic/claude-haiku-4-5-20251001'anthropic/claude-haiku-4-5-20251001
promptYesThe user prompt to complete
systemNoOptional system instruction
max_tokensNoMax output tokens
temperatureNoSampling temperature

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_compliance_generate
Read-onlyIdempotent
Inspect

Generate a compliance report for regulatory frameworks (EU AI Act, ISO 42001, SOC2, NIST). Exports from live audit data.

ParametersJSON Schema
NameRequiredDescriptionDefault
formatNoOutput format: ndjson or csvndjson
frameworkNoFramework: eu-ai-act, iso-42001, soc2, nisteu-ai-act
workspaceNoWorkspace identifierdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_count_tokens
Read-onlyIdempotent
Inspect

Estimate token count for text (chars/4 approximation).

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesText to estimate tokens for

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_decision_cost
Read-onlyIdempotent
Inspect

Analyze cost-per-decision for AI agents. Shows the actual AI cost for each decision, compared to the pre-AI baseline. Answers: 'How much does each AI decision cost?' and 'How does it compare to doing it without AI?'

ParametersJSON Schema
NameRequiredDescriptionDefault
periodNoTime period: 'today', 'this-week', 'this-month', 'all'this-month
workspaceNoWorkspace identifierdefault
agent_nameNoFilter by specific agent
process_nameNoFilter by specific process

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_detect_injection
Read-onlyIdempotent
Inspect

Detect prompt injection attempts in text using guardrail patterns. Also retrieves live guardrails_blocked stats from the gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesText to analyze for injection attempts

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_detect_waste
Read-onlyIdempotent
Inspect

Detect waste and inefficiency in AI operations. Analyzes agent performance, A2A communication overhead, error costs, unused capacity, and cost outliers. Returns specific actionable findings like 'you are losing $3,200/month on error retries' or 'this flow is 5x more expensive than your best-performing flow'. This is the diagnostic tool that creates the buying trigger.

ParametersJSON Schema
NameRequiredDescriptionDefault
daysNoAnalysis window in days
workspaceNoWorkspace identifierdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_end_traceInspect

End an active agent trace and get the session summary. Returns total cost, duration, tool/model call counts, and event count. Triggers post-session anomaly detection (cost spikes, error rate). Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
statusNoFinal session status: 'success', 'failure', or 'timeout'success
session_idYesSession ID from thinkneo_start_trace

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_evaluate_guardrail
Read-onlyIdempotent
Inspect

Evaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider. Returns risk assessment, violations found, and recommendations. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesThe prompt or text content to evaluate for policy violations (max 32,000 characters)
workspaceYesWorkspace whose guardrail policies to apply for this evaluation
guardrail_modeNoEvaluation mode: 'monitor' (log violations only) or 'enforce' (block the request on violation)monitor

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_evaluate_trust_scoreInspect

Evaluate your organization AI Trust Score (0-100) across 10 dimensions: Guardrails, PII Protection, Injection Defense, Audit Trail, Compliance, Model Governance, Cost Controls, Outcome Validation, Observability, and Smart Routing. Returns a score, detailed breakdown, badge level (Platinum/Gold/Silver/Bronze/Unrated), and actionable recommendations. Score is valid for 30 days. Generates a public badge URL for embedding in websites and documentation. Part of the 'From Prompt to Proof' framework. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
org_nameYesOrganization name for the trust score badge (e.g., 'Acme Corp')

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_get_budget_status
Read-onlyIdempotent
Inspect

Check AI budget status including spend vs limit, forecast, and chargeback data from the ThinkNEO gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault
workspaceNoWorkspace name or IDdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_get_compliance_status
Read-onlyIdempotent
Inspect

Get compliance status including framework coverage (EU AI Act, ISO 42001, NIST AI RMF, SOC 2) and governance assessments from the ThinkNEO gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault
frameworkNoFilter by framework: eu-ai-act, iso-42001, nist-ai-rmf, soc2, allall
workspaceNoWorkspace name or IDdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_get_observability_dashboard
Read-onlyIdempotent
Inspect

Get the agent observability dashboard — aggregated metrics for your AI agents. Includes total sessions, events, cost, error rate, latency, top agents, top tools, active alerts, and cost trend over time. Like Datadog, but for AI agents. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
periodNoTime period: '1h', '24h', '7d', or '30d'24h

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_get_proof
Read-onlyIdempotent
Inspect

Retrieve the immutable proof record for a verified claim. Includes the original claim, verification evidence, verifier identity, and a SHA-256 proof hash for tamper detection. This is the 'proof' in 'From Prompt to Proof'. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
claim_idYesUUID of the claim to get proof for

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_get_savings_report
Read-onlyIdempotent
Inspect

Get your AI cost savings report. Shows total requests routed, original cost (what you'd have paid with premium models), actual cost, total savings, savings percentage, breakdown by task type, and model distribution. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
periodNoReport period: '7d' (7 days), '30d' (30 days), or '90d' (90 days)30d

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_get_trace
Read-onlyIdempotent
Inspect

Retrieve the full trace for an agent session. Returns the complete timeline of events (tool calls, model calls, decisions, errors), session metadata, total cost, duration, and any alerts triggered. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
session_idYesSession ID to retrieve the trace for

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_get_trust_badge
Read-onlyIdempotent
Inspect

Get a public AI Trust Score badge by report token. Returns the organization name, score, badge level, and validity period. Use the badge URL to embed the trust badge in websites and documentation. No authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
report_tokenYesThe report token from a trust score evaluation (URL-safe string)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_list_alerts
Read-onlyIdempotent
Inspect

List active alerts for budget, policy, SLA, and security from the ThinkNEO gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault
severityNoFilter by severity: critical, high, medium, low, allall
workspaceNoWorkspace name or IDdefault

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_log_decisionInspect

Log a business decision made by an AI agent. Tracks the AI cost and the business value generated. If a baseline exists for the process, value is auto-calculated from the baseline cost. Example: agent 'support-bot' resolved a 'customer_support_ticket' at $0.03 AI cost, replacing a $12 human-handled ticket. ROI: 400:1.

ParametersJSON Schema
NameRequiredDescriptionDefault
outcomeNoResult: 'success', 'escalated', 'rejected', 'error'success
metadataNoJSON string with additional context
workspaceNoWorkspace identifierdefault
agent_nameYesName of the AI agent that made the decision, e.g. 'support-bot', 'loan-reviewer'
confidenceNoConfidence score 0.0-1.0
ai_cost_usdNoActual AI cost for this decision in USD, e.g. 0.03
process_nameNoLinks to a baseline process for auto ROI calculation
decision_typeYesType of decision, e.g. 'ticket_resolved', 'loan_approved', 'content_reviewed'
value_generated_usdNoExplicit business value in USD. If omitted and process_name has a baseline, auto-calculated.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_log_eventInspect

Log an event within an active agent trace. Supports event types: tool_call, model_call, decision, error, pii_access, guardrail_triggered. Returns event_id and running session cost. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
costNoEstimated cost in USD for this event (e.g., 0.003 for an API call)
metadataNoOptional dict with additional event context
tool_nameNoName of the tool called (for tool_call events)
event_typeYesEvent type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'
latency_msNoLatency in milliseconds for this event
model_nameNoModel used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')
session_idYesSession ID from thinkneo_start_trace
input_summaryNoBrief summary of the input (max 500 chars, truncated if longer)
output_summaryNoBrief summary of the output (max 500 chars, truncated if longer)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_log_risk_avoidanceInspect

Log a risk event that was blocked or avoided by the governance layer. Quantifies the estimated dollar impact of the avoided risk. Examples: PII leak blocked (est. $50K GDPR fine), prompt injection prevented, policy violation caught before production. If estimated_impact_usd is not provided, a default is calculated from severity.

ParametersJSON Schema
NameRequiredDescriptionDefault
severityNoSeverity level: 'low', 'medium', 'high', 'critical'medium
risk_typeYesType: 'pii_leak', 'injection_blocked', 'policy_violation', 'spend_limit', 'compliance_breach', 'data_exfiltration'
workspaceNoWorkspace identifierdefault
agent_nameNoAgent involved, if applicable
descriptionNoBrief description of what was blocked
estimated_impact_usdNoEstimated cost if this risk had materialized in USD

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_manage_secrets
Read-onlyIdempotent
Inspect

Check connector grants and secrets status from the gateway.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_optimize_prompt
Read-onlyIdempotent
Inspect

Analyze prompt and suggest optimizations with live metrics context.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesPrompt text to analyze

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_provider_status
Read-onlyIdempotent
Inspect

Get real-time health and performance status of AI providers routed through the ThinkNEO gateway. Shows latency, error rates, and availability. No authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
providerNoSpecific provider to check: openai, anthropic, google, mistral, xai, cohere, or together. Omit to get status for all providers.
workspaceNoWorkspace context for provider routing configuration (optional)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_read_memory
Read-onlyIdempotent
Inspect

Read Claude Code project memory files. Without arguments, returns the MEMORY.md index listing all available memories. With a filename argument, returns the full content of that specific memory file. Use this to access project context, user preferences, feedback, and reference notes persisted across Claude Code sessions.

ParametersJSON Schema
NameRequiredDescriptionDefault
filenameNoName of the memory file to read (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Omit to get the MEMORY.md index with all available files.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_register_claimInspect

Register an action claim from an AI agent. The agent declares it performed an action (e.g., sent an email, created a PR, wrote a file) and ThinkNEO will verify it actually happened. Returns a claim_id for tracking. Part of the Outcome Validation Loop — 'From Prompt to Proof'. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
actionYesType of action claimed: 'email_sent', 'http_request', 'file_written', 'db_insert', 'pr_created', 'payment_processed', 'message_sent', 'api_call', 'task_completed', 'data_exported', 'notification_sent', 'custom'
targetYesTarget of the action — what was acted upon. Examples: 'user@example.com' (email), 'https://api.example.com/endpoint' (http), '/opt/data/report.pdf' (file), 'usage_log' (db table)
metadataNoOptional verification context. For http_status: {expected_status: 200, method: 'GET'}. For file_exists: {expected_hash: 'sha256...'}. For db_row_exists: {where_column: 'id', where_value: '123'}.
ttl_hoursNoHours until claim expires if not verified (default 24, max 168)
agent_nameNoName of the agent making the claim (e.g., 'marketing-agent')
session_idNoOptional observability session_id to link this claim to a trace
evidence_typeYesHow to verify the claim: 'http_status' (check URL response), 'file_exists' (check file path), 'db_row_exists' (check database row), 'webhook' (wait for callback), 'smtp_delivery' (check email delivery), 'manual' (flag for human review)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_registry_get
Read-onlyIdempotent
Inspect

Get full details for an MCP server package from the ThinkNEO Marketplace. Returns readme, full tools list, version history, reviews, security score, and installation instructions. No authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesPackage name (e.g. 'thinkneo-control-plane', 'filesystem', 'github')

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_registry_installInspect

Get installation config for an MCP server from the ThinkNEO Marketplace. Returns ready-to-use JSON config for Claude Desktop, Cursor, Windsurf, or custom clients. Tracks the download. No authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesPackage name to install (e.g. 'thinkneo-control-plane')
client_typeNoYour MCP client: claude-desktop, cursor, windsurf, or customclaude-desktop

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_registry_publishInspect

Publish an MCP server to the ThinkNEO Marketplace. Validates the endpoint by calling initialize and tools/list, runs automated security scan for secrets and injection patterns, computes a security score (0-100), and stores the entry with version history. Validates the endpoint (calls initialize + tools/list), runs security scan (secrets detection, injection patterns), and stores the entry. Authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesPackage name (lowercase, hyphens allowed, e.g. 'my-mcp-server')
tagsNoTags for discoverability (e.g. ['ai', 'governance', 'security'])
readmeNoFull readme/documentation in markdown
licenseNoLicense (e.g. MIT, Apache-2.0)MIT
repo_urlNoSource code repository URL
transportNoTransport type: streamable-http, sse, or stdiostreamable-http
categoriesNoCategories: governance, security, data, development, productivity, communication, analytics, devops, finance, marketing, other
descriptionYesShort description of what this MCP server does (max 500 chars)
display_nameYesHuman-readable display name
endpoint_urlYesMCP server endpoint URL (e.g. https://my-server.com/mcp)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_registry_review
Idempotent
Inspect

Rate and review an MCP server in the ThinkNEO Marketplace. One review per user per package (updates on repeat). Rating from 1 (poor) to 5 (excellent) with optional comment. Reviews affect the package average rating shown in search results. One review per user per package (updates on repeat). Authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesPackage name to review
ratingYesRating from 1 (poor) to 5 (excellent)
commentNoReview comment (max 2000 chars)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_rotate_key
Destructive
Inspect

Instruct the gateway to rotate an API key.

ParametersJSON Schema
NameRequiredDescriptionDefault
key_prefixYesFirst 8 chars of the key to rotate

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_route_model
Read-onlyIdempotent
Inspect

AI Smart Router — find the cheapest model that meets your quality threshold. Specify your task type and quality requirements, and ThinkNEO will recommend the optimal model with estimated cost and savings vs premium models. Supports 17+ models across Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Alibaba, Cohere, and xAI. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
task_typeYesThe type of AI task: summarization, classification, code_generation, chat, analysis, translation, or embedding
text_sampleNoOptional sample text for better routing. Helps estimate token count and task complexity. Max 500 characters.
max_latency_msNoMaximum acceptable latency in milliseconds. Omit for no limit.
estimated_tokensNoEstimated total tokens for the request (input + output). Default 1000.
quality_thresholdNoMinimum quality score required (0-100). Default 85 = enterprise-grade.
budget_per_requestNoMaximum budget per request in USD. Omit for no limit.
preferred_providersNoComma-separated list of preferred providers (e.g., 'openai,anthropic'). These will be prioritized at similar cost.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_router_explain
Read-onlyIdempotent
Inspect

Explain why the Smart Router would choose a specific model for a task type. Shows both benchmark-based (real outcomes) and static quality estimates, and explains the reasoning behind the recommendation. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
task_typeYesTask type: 'summarization', 'code_generation', 'classification', 'translation', 'analysis', 'chat'
quality_thresholdNoMinimum quality score required (0-100, default 85)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_schedule_demoInspect

Schedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required.

ParametersJSON Schema
NameRequiredDescriptionDefault
roleNoContact's role: cto, cfo, security, engineering, or other
emailYesBusiness email address to receive follow-up from the ThinkNEO team
companyYesCompany or organization name
contextNoAdditional context such as current AI providers used, request volume, or specific use case
interestNoPrimary area of interest: guardrails, finops, observability, governance, or full platform
contact_nameYesFull name of the person requesting the demo
preferred_datesNoPreferred meeting dates, times, and timezone (e.g., 'Tuesdays or Thursdays, 9-11am EST')

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_set_baseline
Idempotent
Inspect

Define the pre-AI cost baseline for a business process. Example: 'customer_support_ticket costs $12 per ticket and takes 15 minutes without AI'. This baseline is used to calculate ROI when agents handle the same process. Call this once per process to establish the comparison point.

ParametersJSON Schema
NameRequiredDescriptionDefault
notesNoAdditional context about this baseline
workspaceNoWorkspace identifierdefault
unit_labelNoWhat one unit represents, e.g. 'ticket', 'review', 'decision', 'document'unit
process_nameYesName of the business process, e.g. 'customer_support_ticket', 'loan_review', 'content_moderation'
cost_per_unit_usdYesPre-AI cost per unit in USD, e.g. 12.00 for a $12 support ticket
avg_duration_minutesNoAverage time in minutes for one unit without AI, e.g. 15

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_simulate_savings
Read-onlyIdempotent
Inspect

Simulate how much your organization would save on AI costs using ThinkNEO Smart Router. Enter your current monthly AI spend and primary model, and see estimated monthly and annual savings with a recommended model mix. No authentication required — try it now!

ParametersJSON Schema
NameRequiredDescriptionDefault
primary_modelNoYour primary model: 'gpt-4o', 'claude-opus-4', 'claude-sonnet-4', 'gpt-4.1', or 'gemini-2.5-pro'gpt-4o
monthly_ai_spendYesYour current monthly AI API spend in USD (e.g., 5000.00)
task_distributionNoJSON string of task distribution, e.g., '{"chat": 0.3, "summarization": 0.2, "code_generation": 0.2, "classification": 0.15, "analysis": 0.1, "translation": 0.05}'. Values should sum to ~1.0. Omit for default enterprise distribution.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_sla_breaches
Read-onlyIdempotent
Inspect

View SLA breach history — which SLAs were breached, by which agents, actual vs threshold values, and resolution status. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
daysNoDays to look back (default 30)
agent_nameNoFilter by agent name

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_sla_dashboard
Read-onlyIdempotent
Inspect

SLA overview dashboard — all agents, current status, error budgets, and recent breaches (7d). The SRE dashboard for AI agents. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_sla_define
Idempotent
Inspect

Define or update an SLA (Service Level Agreement) for an AI agent. Set accuracy, quality, cost, safety, or latency thresholds with automatic breach detection and configurable actions (alert, escalate, disable, switch_model). Like SRE SLOs but for AI agent outcomes. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
metricYesMetric to monitor: 'accuracy' (outcome verification rate %), 'response_quality' (avg quality score), 'cost_efficiency' (cost per verified outcome), 'safety' (guardrail pass rate %), 'latency' (avg response ms)
windowNoRolling window: '1h', '24h', '7d', or '30d'7d
thresholdYesTarget threshold value (e.g., 95.0 for 95% accuracy)
agent_nameYesAgent name to set SLA for (e.g., 'support-bot', 'finance-agent')
breach_actionNoAction on breach: 'alert' (notify), 'escalate' (notify + flag), 'disable' (stop agent), 'switch_model' (fallback model)alert
threshold_directionNo'min' = actual must be >= threshold (for accuracy, quality). 'max' = actual must be <= threshold (for cost, latency).min

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_sla_status
Read-onlyIdempotent
Inspect

Check current SLA status for all agents or a specific agent. Shows actual metric values vs thresholds, healthy/breached status, and error budget remaining. Automatically records breaches. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
agent_nameNoOptional: specific agent name. Leave empty for all agents.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_start_traceInspect

Start a new agent observability trace. Creates a session that tracks all tool calls, model calls, decisions, and errors for an AI agent run. Returns a session_id to use with thinkneo_log_event and thinkneo_end_trace. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
metadataNoOptional dict with additional context (e.g., {"task": "email-draft", "user_id": "u123"})
agent_nameYesName of the agent being traced (e.g., 'marketing-agent', 'support-bot')
agent_typeNoType of agent: 'assistant', 'autonomous', 'workflow', 'pipeline', or 'generic'generic

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_usage
Read-onlyIdempotent
Inspect

Returns usage statistics for your ThinkNEO API key. Shows calls today, this week, this month, monthly limit, remaining calls, top tools used, estimated cost, and current tier. Works without authentication (returns general info).

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_verification_dashboard
Read-onlyIdempotent
Inspect

Aggregated outcome verification metrics — verification rates, failure patterns, agent reliability rankings, and daily trends. Shows how reliably your AI agents are delivering verified outcomes. 'Datadog for AI outcomes'. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
periodNoTime period: '24h', '7d', or '30d'7d

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_verify_claim
Idempotent
Inspect

Trigger verification of a registered action claim. Runs the appropriate verification adapter (HTTP check, file check, database check, etc.) and returns the result with evidence. If already verified, returns cached result (use force=true to re-verify). Part of the Outcome Validation Loop — 'From Prompt to Proof'. Requires authentication.

ParametersJSON Schema
NameRequiredDescriptionDefault
forceNoForce re-verification even if already verified/failed
claim_idYesUUID of the claim to verify (from thinkneo_register_claim)

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
thinkneo_write_memory
Idempotent
Inspect

Write or update a Claude Code project memory file (.md). Persists project context, user preferences, feedback, and reference notes across Claude Code sessions. Filename must end in .md with lowercase alphanumeric characters. Path traversal is blocked. Requires authentication.Use this to persist project context, user preferences, feedback, and reference notes across Claude Code sessions. The filename must end in .md and contain only lowercase letters, digits, underscores, and hyphens (e.g. 'user_fabio.md', 'project_new_feature.md'). Path traversal is blocked.

ParametersJSON Schema
NameRequiredDescriptionDefault
contentYesFull markdown content to write to the file.
filenameYesName of the memory file to write (e.g. 'user_fabio.md', 'project_thinkneodo_droplet.md'). Must end in .md.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.