Skip to main content
Glama

Server Details

Read-only MCP server that answers questions about turva.dev from its published data. Five tools return JSON: the service catalog with prices, contact and operator details, engagement principles and dated agent-readiness and security evidence with verification links. Connect over Streamable HTTP. You need no API key. The server does not scan other websites or run audits.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.7/5.0

Scored across 5 tools

Disambiguation5/5

Each tool returns a distinct slice of static data: readiness score, security scans, service catalog, principles, and contact/legal details. The descriptions explicitly cross-reference the nearest neighbors (e.g. get_agent_readiness vs get_security_evidence, get_principles vs get_services vs get_contact), so an agent can route unambiguously.

Naming Consistency5/5

All five tools follow the same get_<noun> pattern with a single verb style and consistent snake_case. There are no mixed conventions or versioned/vague names.

Tool Count5/5

Five read-only tools is well matched to a small static informational surface; each tool maps to a separate question category and none appears redundant. Nothing feels padded or conspicuously absent.

Completeness4/5

The surface covers the core questions about turva.dev: offering and pricing, terms, contact/legal, principles, and both evidence measurements, with the sample report reachable via sample_url in the catalog. Minor gaps remain, such as no dedicated tool for a sample/worked-report retrieval or an FAQ, but agents can route around these through get_services and get_contact.

Publisher details

Operator
turva.dev, a sole trader business run by Erik Rekola in Tampere, Finland, Business ID 3600281-7. · Publisher source
Vendor relationship
First-party · Publisher source
Privacy policy
Not provided
Restrictions
None. The endpoint is public and read-only. It needs no account, authentication, API key, paid plan, admin approval or custom OAuth app, and it is not limited by region. · Publisher source

Available Tools

5 tools
get_agent_readinessAgent-readiness scoreA
Read-onlyIdempotent
Inspect

Returns turva.dev's own agent-readiness score from an independent public scanner (isitagentready.com), including category sub-scores, with the measurement date and a link to the scanner's start page, where a new check can be run (the link does not open the recorded reading). Use this when a user asks how turva.dev scores, whether its claims are verifiable, or what proof backs the audit service. For web-security scan results, which are a separate measurement, use get_security_evidence instead. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.

Inputs: no named parameters. Returns: note, scans, domain, measured_at

get_contactContact and operator detailsA
Read-onlyIdempotent
Inspect

Returns who runs turva.dev and the official ways to reach it. The operator details give the legal form, Business ID, VAT ID and postal address. The rest gives the email address, the Signal link, the LinkedIn profile, the correspondence languages, the first-reply time, the access an audit needs, and links to the company page and to the legal page that states the terms, the privacy notice and how data is handled. Use this when a user asks who is behind turva.dev, for its legal or imprint details, how to contact it, how to start an audit or what access has to be granted. For what is sold and what it costs use get_services instead. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.

Inputs: no named parameters. Returns: email, signal, linkedin, location, +7 more

get_principlesEngagement principlesA
Read-onlyIdempotent
Inspect

Returns turva.dev's four engagement principles, each with its reason: async-only, least access, each fix checked with a scanner or a direct test, and open and verifiable. Use this when a user asks what turva.dev stands by or why it works the way it does, for example why there are no calls. For the terms of an engagement, its scope, access, dates, payment and prices, use get_services instead, and for how to start use get_contact. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.

Inputs: no named parameters. Returns: model, rules

get_security_evidenceWeb-security scan evidenceA
Read-onlyIdempotent
Inspect

Returns the latest public web-security scan results for turva.dev's own domain (Hardenize, Internet.nl site and mail), each with its scan date. Use this when a user asks about turva.dev's own security posture or wants evidence beyond agent-readiness scores. For the agent-readiness score itself, which is a separate measurement, use get_agent_readiness instead. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.

Inputs: no named parameters. Returns: note, scans, domain, measured_at

get_servicesService catalog and pricingA
Read-onlyIdempotent
Inspect

Returns turva.dev's service catalog: the agent-readiness audit, advisory, implementation, agent operations, and MCP server design, with pricing and the terms of an engagement: scope, access, dates and payment. Fixed list prices apply to the audit, advisory and implementation. Agent operations and MCP server design are on request. The catalog also lists one implementation add-on that carries a fixed price and is sold only with the audit it follows, bought with it, with its report, or after the report and before implementation starts. It also lists active security testing, an add-on to the audit that is priced by quote for each written scope, under quoted_add_ons. The audit links a published sample report in sample_url, a fictional worked example of the deliverable. Use this when a user asks what turva.dev offers, what it costs, what the terms of an engagement are, or what a delivered report looks like. For the standing rules turva.dev keeps in every engagement use get_principles instead, and for how to reach turva.dev or start an audit use get_contact. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.

Inputs: no named parameters. Returns: currency, services, engagement, pricing_note, +4 more

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
      B
      maintenance
      Read-only MCP server that answers questions about turva.dev from its published data. Five tools return JSON: the service catalog with prices, contact and operator details, engagement principles and dated agent-readiness and security evidence with verification links. Connect over Streamable HTTP. You need no API key. The server does not scan other websites or run audits.
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Exposes 8 read-only Trust Vault tools over MCP (Streamable HTTP) for querying protocol overview, tokens, market rates, orders, platform stats, fees, and currencies. Enables on-chain reads and static config without wallet or signing.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      A read-only MCP server that lets an AI client query multi-account, multi-region AWS estates through 24 typed tools — identity checks, EC2/S3/VPC inventory, IAM hygiene, GuardDuty and Security Hub posture, backups, cost totals, and dry-run simulations. It cannot mutate AWS: results are capped at 50 rows and every call is written to an audit trail as harness:mcp.
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      A read-only MCP server that serves the LifeScored rulebook and exact math, the input schema for collecting fields, a plain-English methodology and fairness explanation, and instructions for proposing improvements. It handles only reads, sends no personal data, and requires no authentication.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources