Skip to content
MCPSTAMP
MCP server report

Boundra MCP server

io.boundra/boundra

We checked this server on 2 November 2026 with McpStamp Check engine 1.2.0. It scored 73 of 100 (grade C), higher than 18.9% of the 33,003 registry servers that responded over HTTPS that day. Ready for Gemini and MCP Registry. Not ready for Claude and ChatGPT.

Measured facts

Score
73C
Sign-in
No sign-in
Tools listed
11
Protocol version
2025-11-25
Stores

Store readiness

StoreStatusReason
Claude Connectors Directory Not ready Blocked by readOnlyHint or destructiveHint on every tool and Human-readable title on every tool.
ChatGPT app directory Not ready Blocked by readOnlyHint or destructiveHint on every tool, Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT) and Human-readable title on every tool.
Gemini Connected Apps Ready No blocking check failed.
Official MCP Registry Ready No blocking check failed.

MCP Registry ready means a valid public remote for the registry, not that the server is listed in a store.

Fixes

6 checks to fix

  1. Fails

    readOnlyHint or destructiveHint on every tool

    tool_annotations

    Blocks Claude and ChatGPT.

    Measured 11/11 tools set neither readOnlyHint nor destructiveHint: evaluate_payment, request_policy_change, get_policy, get_spend_report, get_audit_trail and 6 more

    Set annotations.readOnlyHint: true on read-only tools and destructiveHint: true on tools that modify or delete data (Claude needs one of them on every tool; ChatGPT needs all three hints, see tool_open_world).

  2. Fails

    Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT)

    tool_open_world

    Blocks ChatGPT.

    Measured 11/11 tools miss an explicit hint: evaluate_payment, request_policy_change, get_policy, get_spend_report, get_audit_trail and 6 more

    Set readOnlyHint, destructiveHint and openWorldHint to explicit true/false on every tool (OpenAI app review requires all three).

  3. Fails

    Human-readable title on every tool

    tool_titles

    Blocks Claude and ChatGPT.

    Measured 11/11 without title: evaluate_payment, request_policy_change, get_policy, get_spend_report, get_audit_trail and 6 more

    Add a short human-readable "title" to every tool (shown in store UIs and consent screens).

  4. Warning

    serverInfo name and version

    server_info

    Measured serverInfo {"name":"boundra-hosted","version":""}

    Return serverInfo with both name and version (and a title) in the initialize result.

  5. Warning

    Tool descriptions

    tool_descriptions

    Measured 3 under 60 chars: get_spend_report, get_audit_trail, list_policy_requests

    Keep each tool description between 60 and 2000 characters: when to use it, what it returns, key limits.

  6. Warning

    initialize latency

    latency

    Measured 1522 ms

    Bring initialize under 1.5 s: avoid cold starts and upstream calls in the handshake.

11 checks passed, 10 did not run

Passed. Served over HTTPS, initialize over Streamable HTTP, Supported protocol version negotiated, JSON or SSE response Content-Type, JSON-RPC error for unknown method, GET answers SSE or 405, Server instructions, tools capability declared, tools/list returns tools, inputSchema is an object schema, Tool names are valid and portable.

Not run. Sign-in method the store supports (OAuth or none), 401 carries WWW-Authenticate resource_metadata, Protected resource metadata (RFC 9728), Resource metadata "resource" equals the server URL, Authorization server metadata (RFC 8414 / OIDC), First metadata URL Gemini tries answers 200 with the required fields, issuer equals the authorization_servers entry; token_endpoint_auth_methods_supported (ChatGPT), PKCE S256 advertised, Client registration (DCR or Client ID Metadata Documents), refresh_token grant advertised. The server asks for no sign-in, so the OAuth checks do not apply.

Run a fresh check

This page is the 2 November 2026 snapshot. If you maintain this server and have shipped fixes since then, re-check it. The live check and the badge show the current result, and the next snapshot will pick up the change.

Re-check now

Badge

README badge

The badge shows the latest score for this URL and links to this report.

McpStamp score for Boundra

Markdown

[![McpStamp score](https://www.mcpstamp.com/badge?url=https%3A%2F%2Fapi.boundra.io%2Fmcp)](https://www.mcpstamp.com/r/io-boundra-boundra/)

HTML

<a href="https://www.mcpstamp.com/r/io-boundra-boundra/"><img src="https://www.mcpstamp.com/badge?url=https%3A%2F%2Fapi.boundra.io%2Fmcp" alt="McpStamp score" height="20"></a>
Registry entry

About this server

Allow, ask, or veto - a policy decision point your agent consults before signing any payment
Registry name
io.boundra/boundra
Remote URL
https://api.boundra.io/mcp
Version
0.1.2
Source
github.com/gobeyondfj-cmd/boundra
Website
boundra.io
Checked
2 November 2026, engine 1.2.0, no credentials

The description above is the server's own text from the official MCP Registry. If a result looks wrong, run a fresh check and email support@zovo.one with the report link.

More grade C servers

All grade C servers · All server reports · State of MCP readiness, November 2026