Countersign by Signalry
REMOTE · COUNTERSIGN.SIGNALRY.AI
Countersign by Signalry: live checks of an agent's done claim. First call: start {subject}
Available components
Last scanned (19 hours ago)
Scores higher than 62% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Security
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 Security80
- 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. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- 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 Usability75
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1217 tokens (~135/item across 9 items; 9 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 Management23
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 50% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 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
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
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.
- 20 Nov 26 +4
- The server rewrote its instructions, which are the text every model session reads security
- Tool “check_reply_gate” rewrote its description, which is the text the model reads security
- Tool “find_tools” rewrote its description, which is the text the model reads security
- Tool “get_track_record” rewrote its description, which is the text the model reads security
- Tool “request_key” rewrote its description, which is the text the model reads security
- Tool “start” rewrote its description, which is the text the model reads security
- Tool “verify_claim” rewrote its description, which is the text the model reads security
- Tool “try_check” rewrote its description, which is the text the model reads security
- Tool “submit_claim” rewrote its description, which is the text the model reads security
- Schema quality: 165 → 135 ▲ functional
- The server now declares the “prompts” capability functional
- First check of Schema quality: 100 functional
- Schema quality: fair → good functional
- New prompt “check_site” functional
- New prompt “see_example” functional
- New tool “show_example” functional
- “start” added an optional parameter “api_key” cosmetic
- “try_check” reworded the description of “subject” cosmetic
- 19 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “verify_claim” rewrote its description, which is the text the model reads security
- Tool “try_check” rewrote its description, which is the text the model reads security
- Tool “submit_claim” rewrote its description, which is the text the model reads security
- Tool “request_key” rewrote its description, which is the text the model reads security
- Schema quality: 150 → 165 ▼ functional
- Tool coverage: 33% → 47% ▲ functional
- Server version: 0.1.1 → 0.1.2 functional
- New tool “start” functional
- “verify_claim” added an optional parameter “api_key” cosmetic
- “submit_claim” added an optional parameter “api_key” cosmetic
- “request_key” reworded the description of “public” cosmetic
- 16 Nov 26 +4
- The server rewrote its instructions, which are the text every model session reads security
- Tool “find_tools” rewrote its description, which is the text the model reads security
- Schema quality: 358 → 150 ▲ functional
- Tool coverage: 11% → 33% ▲ functional
- New tool “request_key” functional
- “submit_claim” added an optional parameter “full” cosmetic
- 15 Nov 26 0
- Stability: unverified → 0.03 ▲ functional
- 14 Nov 26 65
First indexed and scored.
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 21 Nov 2026 · Probed https://countersign.signalry.ai/mcp?ref=mcp-registry
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=countersign.signalry.ai | CN=YR1,O=Let's Encrypt,C=US | 19 Oct 2026 | 17 Jan 2027 | RSA 2048 | SHA256-RSA | 63736e7feb63e617d9b9b91e727292be74e |
| SANs: countersign.signalry.ai | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of countersign.signalry.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| signalry.ai. | No DS | 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 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
| x-content-type-options | nosniff |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://countersign.signalry.ai/mcp?ref=mcp-registry | Verified | 200 | |
| http (plaintext) | http://countersign.signalry.ai/mcp?ref=mcp-registry | HTTPS enforced | 308 | https://countersign.signalry.ai/mcp?ref=mcp-registry |
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_reply_gate ~47
Checks a drafted reply before it says live or done: cited claims must be verified and fresh. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| fresh_within | string | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
find_tools ~39
Lists the other tools (request_agent_key, get_status, search_claims, more) with arguments. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | – | – |
No output schema declared.
No examples provided.
get_track_record ~35
An agent's public track record, or the ranked table when agent is omitted. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | – |
No output schema declared.
No examples provided.
request_key ~91
Issues a csk_ key without filing a claim: {} or {public: true} returns an unbound key now; {agent} a claimable link. Then start {subject, api_key} or submit_claim.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | claimable-link path (proof later) |
| public | boolean | – | true or omitted with no agent: a csk_ key now (identity unbound) |
No output schema declared.
No examples provided.
show_example ~55
Shows one real claim from the public ledger that counts as verified now: statement, the checks this service ran, verdict and receipt URL. No arguments; writes nothing. Use it to see a receipt before checking a host of your own.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
start ~116
Issues a csk_ key and files a first claim with it in one call: https://<subject>/ answers 200 with valid TLS, checked now; it counts if both pass. subject: a bare hostname the caller operates. Writes a key and one unlisted claim (no new key with api_key).
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | ks-1: a csk_ key you already hold; start files the first claim with it |
| subject | string | yes | bare hostname you operate, e.g. docs.example.org |
No output schema declared.
No examples provided.
submit_claim ~145
Records a claim about work (a deploy is live, a page contains a text, a PR merged) and runs its checks now. It counts only if the checks pass, a check targets what the statement names, and a key is sent (Bearer or api_key); no key yet: start, or request_key {public: true}.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | mf-1: your csk_ key, for clients that set headers only at connect (the header wins when both are sent) |
| checks | array | yes | – |
| full | boolean | – | true: whole claim; default compact |
| statement | string | yes | – |
| subject | string | yes | – |
No output schema declared.
No examples provided.
try_check ~85
Checks a public hostname live now: an https GET of / (status only) and its TLS certificate. Takes a bare hostname such as docs.example.org. No key; writes nothing. Returns the start and submit_claim arguments that would record the same checks.
| Name | Type | Req | Description |
|---|---|---|---|
| subject | string | yes | bare public hostname, e.g. docs.example.org (no scheme, path, port or IP) |
No output schema declared.
No examples provided.
verify_claim ~72
Re-runs the checks of the caller's own claim and appends a receipt. Needs the caller's key.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | – | mf-1: your csk_ key, for clients that set headers only at connect (the header wins when both are sent) |
| id | string | yes | – |
No output schema declared.
No examples provided.
How do I install the Countersign by Signalry MCP server?
Countersign by Signalry is a hosted endpoint at https://countersign.signalry.ai/mcp?ref=mcp-registry, 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 · countersign.signalry.ai
claude mcp add --transport http ai-signalry-countersign 'https://countersign.signalry.ai/mcp?ref=mcp-registry'
What is the Countersign by Signalry MCP server?
Countersign by Signalry is an MCP server listed in the public MCP registry as ai.signalry/countersign. Countersign by Signalry: live checks of an agent's done claim. First call: start {subject}. This page covers its hosted endpoint (https://countersign.signalry.ai/mcp?ref=mcp-registry).
Is the Countersign by Signalry MCP server safe to use?
Countersign by Signalry scores 75 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 Countersign by Signalry MCP server expose?
Countersign by Signalry exposes 9 tools: show_example, try_check, start, submit_claim, verify_claim, and 4 more. Their descriptions and schemas cost roughly 685 tokens of context every time the server is loaded.
Does the Countersign by Signalry MCP server require authentication?
No. We connected to Countersign by Signalry without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Countersign by Signalry MCP server still maintained?
Countersign by Signalry is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Countersign by Signalry MCP server?
VerifyMCP ran 13 checks on Countersign by Signalry, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.