protogrid
REMOTE · API.PROTOGRID.DEV · SCANNED OCT 6
Find MCP servers by intent and get exactly how to connect to them right now. No proxying.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability69
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 736 tokens (~147/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
- Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 86% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the protogrid MCP server?
protogrid is a hosted endpoint at https://api.protogrid.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.protogrid.dev
claude mcp add --transport http dev-protogrid-registry 'https://api.protogrid.dev/mcp'
{
"mcpServers": {
"dev-protogrid-registry": {
"url": "https://api.protogrid.dev/mcp"
}
}
} {
"servers": {
"dev-protogrid-registry": {
"type": "http",
"url": "https://api.protogrid.dev/mcp"
}
}
} [mcp_servers.dev-protogrid-registry] url = "https://api.protogrid.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"dev-protogrid-registry": {
"type": "remote",
"url": "https://api.protogrid.dev/mcp",
"enabled": true
}
}
} openclaw mcp add dev-protogrid-registry --url 'https://api.protogrid.dev/mcp' --transport streamable-http
mcp_servers:
dev-protogrid-registry:
url: "https://api.protogrid.dev/mcp" {
"McpServers": {
"dev-protogrid-registry": {
"Transport": "http",
"Url": "https://api.protogrid.dev/mcp"
}
}
} assistant mcp add dev-protogrid-registry -t streamable-http -u 'https://api.protogrid.dev/mcp'
{
"mcpServers": {
"dev-protogrid-registry": {
"type": "http",
"url": "https://api.protogrid.dev/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 6 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 43. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 4 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Sept 26 0
- Schema quality: 129 → 147 ▼ functional
- “search” added an optional parameter “exclude_quality_flags” cosmetic
- “search” added an optional parameter “min_quality” cosmetic
- “search” added an optional parameter “owner_verified” cosmetic
- “search” added an optional parameter “quality_flags” cosmetic
- 29 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “check_server” now declares an output schema ▲ functional
- Tool “get_connection” now declares an output schema ▲ functional
- Tool “get_server” now declares an output schema ▲ functional
- Tool “list_tools” now declares an output schema ▲ functional
- Tool “search” now declares an output schema ▲ functional
- First check of Tool coverage: 100 functional
- Schema quality: excellent → good functional
- Server version: 0.2.0 → 0.3.0 functional
- 28 Sept 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Sept 26 +7
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 6 Oct 2026 · Probed https://api.protogrid.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=protogrid.dev | CN=YE1,O=Let's Encrypt,C=US | 20 Sept 2026 | 19 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 5570deb34fa11951d511051de9e9fe6d9ee |
| SANs: *.protogrid.dev, protogrid.dev | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.protogrid.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| protogrid.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.protogrid.dev/mcp | Verified | 200 | |
| http (plaintext) | http://api.protogrid.dev/mcp | HTTPS enforced | 301 | https://api.protogrid.dev/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_server Check an MCP server URL ~150
Probe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories. Pass `url` to start a check (waits up to 25 s for the result), or `id` to read one. Quota: a few checks per hour anonymously, more with an API key.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | – | A check id returned earlier, to read its result |
| url | string | – | The server's streamable HTTP or SSE URL, e.g. https://mcp.example.com/mcp. Never include credentials. |
| wait | integer | – | Seconds to wait for the result (default 25) |
| Name | Type | Req | Description |
|---|---|---|---|
| disclaimer | string | yes | – |
| error | string | – | – |
| finished_at | string|null | yes | – |
| id | string | yes | Pass as id to read the result later |
| next_actions | array | yes | Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill) |
| page | string | yes | Shareable result page |
| requested_at | string | yes | – |
| result | object | – | Present when status is done |
| server | string|null | yes | The catalog server listing this URL, if any |
| status | string | yes | – |
| url | string | yes | – |
No examples provided.
get_connection Get a connection block ~64
Minimal connection block for the preferred remote (or package) with ${SECRET} placeholders, formatted for a target client. Secrets are never accepted or returned.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Official reverse-DNS name |
| target | string | – | Output format (default mcpServers) |
| Name | Type | Req | Description |
|---|---|---|---|
| autonomous | boolean | yes | – |
| class | string | yes | R0 remote no auth, R1 static secret, R2 OAuth, L0 local package |
| connection | – | yes | The block for the target client: an object for JSON targets, a string for text ones |
| content_type | string | yes | – |
| human_steps | array | yes | – |
| key | string | yes | Suggested name for the server in the client configuration |
| kind | string | yes | – |
| next_actions | array | yes | Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill) |
| placeholders | string | yes | – |
| secrets | array | yes | Placeholders to replace with values you hold |
| server | string | yes | – |
| target | string | yes | – |
No examples provided.
get_server Get a server descriptor ~84
Official server.json plus connectability (class, remotes with auth/health, packages), current tools, trust breakdown and identity for one server name.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Official reverse-DNS name, e.g. io.github.acme/acme-mcp |
| schemas | boolean | – | Include tool input/output schemas (default false; use list_tools for full schemas) |
| Name | Type | Req | Description |
|---|---|---|---|
| _meta | object | yes | protogrid enrichment next to the official registry metadata |
| next_actions | array | yes | Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill) |
| server | object | yes | The official server.json as published |
No examples provided.
list_tools List a server's tools ~58
Every current tool of a server with full input/output schemas, paginated by tool name.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from the previous page |
| limit | integer | – | – |
| name | string | yes | Official reverse-DNS name |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | yes | – |
| next_actions | array | yes | Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill) |
| next_cursor | string|null | yes | Pass as cursor for the next page; null on the last page |
| server | string | yes | – |
| tools | array | yes | – |
No examples provided.
search Search MCP servers by intent ~266
Hybrid (keyword + semantic) search over servers and their tools. Filter by connection class to keep only what you can reach autonomously (R0, R1).
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| class | array | – | Connection classes to keep, e.g. ['R0','R1'] |
| exclude_flags | array | – | Trust flags, any of which excludes a server, e.g. ['multi-version-spam','duplicate-repo'] |
| exclude_quality_flags | array | – | Quality flags, any of which excludes a server, e.g. ['known-vulns'] |
| flags | array | – | Trust flags that must all be present |
| limit | integer | – | Results to return (default 10) |
| min_quality | integer | – | Minimum quality score 0-100; unscored servers are left out |
| min_trust | integer | – | Minimum trust score 0-100 |
| owner_verified | boolean | – | true: only servers whose owner proved control of the namespace (not an audit) |
| q | string | yes | What you want to do, in plain words, e.g. 'send an email' or 'query postgres' |
| quality_flags | array | – | Quality flags that must all be present |
| transport | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | yes | – |
| mode | string | yes | – |
| next_actions | array | yes | Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill) |
| query | string | yes | – |
| results | array | yes | – |
No examples provided.
What is the protogrid MCP server?
protogrid is an MCP server listed in the public MCP registry as dev.protogrid/registry. Find MCP servers by intent and get exactly how to connect to them right now. No proxying. This page covers its hosted endpoint (https://api.protogrid.dev/mcp).
Is the protogrid MCP server safe to use?
protogrid scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the protogrid MCP server expose?
protogrid exposes 5 tools: search, get_server, list_tools, get_connection, check_server. Their descriptions and schemas cost roughly 622 tokens of context every time the server is loaded.
Does the protogrid MCP server require authentication?
No. We connected to protogrid without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the protogrid MCP server still maintained?
protogrid is still listed as active in the MCP registry. We last reached this channel on 6 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.