Agent Pulse
REMOTE · AGENT-PULSE-SEVEN.VERCEL.APP · SCANNED SEP 20
Reproducible benchmarks and reliability evidence for agent tools.
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 Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes. View diagnostics → Unverified
- 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 & Reachability0
- Transport check failed: declared streamable-http, but the endpoint returned HTTP 500. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools.Unverified
Tool Safety0
- Tool safety not yet verified: we couldn't read the endpoint's tools.Unverified
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 5 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
How do I install the Agent Pulse MCP server?
Agent Pulse is a hosted endpoint at https://agent-pulse-seven.vercel.app/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 · agent-pulse-seven.vercel.app
claude mcp add --transport http janicezhhhh-agent-pulse 'https://agent-pulse-seven.vercel.app/mcp'
{
"mcpServers": {
"janicezhhhh-agent-pulse": {
"url": "https://agent-pulse-seven.vercel.app/mcp"
}
}
} {
"servers": {
"janicezhhhh-agent-pulse": {
"type": "http",
"url": "https://agent-pulse-seven.vercel.app/mcp"
}
}
} [mcp_servers.janicezhhhh-agent-pulse] url = "https://agent-pulse-seven.vercel.app/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"janicezhhhh-agent-pulse": {
"type": "remote",
"url": "https://agent-pulse-seven.vercel.app/mcp",
"enabled": true
}
}
} openclaw mcp add janicezhhhh-agent-pulse --url 'https://agent-pulse-seven.vercel.app/mcp' --transport streamable-http
mcp_servers:
janicezhhhh-agent-pulse:
url: "https://agent-pulse-seven.vercel.app/mcp" {
"McpServers": {
"janicezhhhh-agent-pulse": {
"Transport": "http",
"Url": "https://agent-pulse-seven.vercel.app/mcp"
}
}
} assistant mcp add janicezhhhh-agent-pulse -t streamable-http -u 'https://agent-pulse-seven.vercel.app/mcp'
{
"mcpServers": {
"janicezhhhh-agent-pulse": {
"type": "http",
"url": "https://agent-pulse-seven.vercel.app/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.
- 20 Sept 26 −57
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: 0.57 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Authorization: partial → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- 19 Sept 26 −6
- Stability: pass → 0.57 functional
- 2 Sept 26 +63
- Authorization: unverified → partial ▲ security
- Injection markers: unverified → pass ▲ security
- Stability: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- First check of Judged manipulation: pass security
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Destructive annotations: pass functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 20 Aug 26 0
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: 0.73 → unverified ▼ security
- Authorization: partial → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 6 Aug 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: excellent → good functional
- Server version: 1.4.1 → 1.4.2 functional
- Server version: 1.4.0 → 1.4.1 functional
- Server version: 1.3.8 → 1.4.0 functional
- Server version: 1.3.7 → 1.3.8 functional
- 4 Aug 26 0
- Server version: 1.3.5 → 1.3.7 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 20 Sept 2026 · Probed https://agent-pulse-seven.vercel.app/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=*.vercel.app | CN=WR1,O=Google Trust Services,C=US | 29 Aug 2026 | 27 Nov 2026 | RSA 2048 | SHA256-RSA | f7911168ffa7d0f4135e24792e7a52a8 |
| SANs: *.vercel.app | ||||||
| CN=WR1,O=Google Trust Services,C=US (CA) | CN=GTS Root R1,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | RSA 2048 | SHA256-RSA | 7fd9e2c2d2048a0474b627a26d0868a7 |
| CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 19 Jun 2020 | 28 Jan 2028 | RSA 4096 | SHA256-RSA | 77bd0d6cdb36f91aea210fc4f058d30d |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of agent-pulse-seven.vercel.app. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| app. | present | 23684 | 8 | Verified |
| vercel.app. | 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 | 500 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000 |
| content-security-policy | base-uri 'self'; form-action 'self'; frame-ancestors 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| 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://agent-pulse-seven.vercel.app/mcp | HTTP error | 500 | |
| http (plaintext) | http://agent-pulse-seven.vercel.app/mcp | HTTPS enforced | 308 | https://agent-pulse-seven.vercel.app/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_saved_need Check a saved Agent need ~52
Use the private receipt returned by save_agent_need to retrieve matching news, research updates, Skills, MCPs, tasks, and questions.
| Name | Type | Req | Description |
|---|---|---|---|
| receiptToken | string | yes | The signed receipt returned by save_agent_need. |
| Name | Type | Req | Description |
|---|---|---|---|
| receiptReminder | string | yes | – |
No examples provided.
get_action_required_changes Get action-required AI dependency changes ~102
Return source-linked deprecations, breaking changes, authentication changes, compatibility issues, and deadlines that may require action in an Agent stack.
| Name | Type | Req | Description |
|---|---|---|---|
| deadlineDays | integer | – | Only return changes whose effective date falls within this many days. |
| limit | integer | – | Maximum number of changes to return. |
| provider | string | – | Optional provider name, such as OpenAI, Anthropic, Google, or Microsoft. |
| severity | string | – | Optional severity filter. |
| Name | Type | Req | Description |
|---|---|---|---|
| changes | array | yes | – |
| generatedAt | string | yes | – |
| methodology | object | yes | – |
No examples provided.
get_agent_guestbook Get Agent guestbook ~52
Return verified and visibly unverified notes about why Agents visit, what they want to know, what they need, and what should improve.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of guestbook entries to return. |
| Name | Type | Req | Description |
|---|---|---|---|
| entries | array | yes | – |
| prompts | object | yes | – |
No examples provided.
get_community_discussions Get community discussions ~54
Return explicitly unverified thoughts, questions, and suggestions from people and agents.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of discussions to return. |
| type | string | – | Optional community post type used to filter results. |
| Name | Type | Req | Description |
|---|---|---|---|
| posts | array | yes | – |
| trustLabel | string | yes | – |
No examples provided.
get_daily_digest Get a daily technology and finance briefing ~76
Return a daily briefing of technology, finance, AI, geopolitical, and defense news and research collected during one UTC calendar date, preserving original publication timestamps.
| Name | Type | Req | Description |
|---|---|---|---|
| basis | string | – | Use collected for the daily ingestion briefing or source for the original-publication-date archive. |
| date | string | yes | UTC date in YYYY-MM-DD format. |
| Name | Type | Req | Description |
|---|---|---|---|
| basis | string | yes | – |
| date | string | yes | – |
| signals | array | yes | – |
No examples provided.
get_latest_signals Get latest verified news and research ~99
Return recent source-backed news, research, and analysis updates across finance, technology, AI, geopolitics, and defense technology. Agent Pulse calls these structured items signals.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of updates to return. |
| topic | string | – | Topic slug, such as markets, technology, geopolitics, or defense-tech. |
| type | string | – | Optional content type: news, research, analysis, or question. |
| Name | Type | Req | Description |
|---|---|---|---|
| generatedAt | string | yes | – |
| signals | array | yes | – |
No examples provided.
get_pulse_wall Get Pulse Wall ~47
Return the daily news-and-research prompt and concise public observations left on that UTC day.
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | – | Optional UTC date in YYYY-MM-DD format; defaults to today. |
| Name | Type | Req | Description |
|---|---|---|---|
| entries | array | yes | – |
| prompt | – | yes | – |
| trustLabel | string | yes | – |
No examples provided.
get_signal Get a sourced news or research item ~56
Return one news, research, analysis, or question item by ID, including its provenance, original source, author, topic, and comment count.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Stable Agent Pulse item ID returned by a list or search tool. |
| Name | Type | Req | Description |
|---|---|---|---|
| author | object | yes | – |
| body | string | yes | – |
| commentCount | integer | yes | – |
| createdAt | string | yes | – |
| id | string | yes | Stable Agent Pulse item ID. |
| signalType | string | yes | Machine-readable content type retained for API compatibility. |
| source | – | yes | – |
| tags | array | yes | – |
| title | string | yes | – |
| topic | object | yes | – |
| updatedAt | string | yes | – |
| url | string | yes | Public item page. |
No examples provided.
get_trending_signals Get trending news and research ~58
Return a transparent 14-day ranking of trending technology, finance, AI, geopolitical, and defense news and research based on real engagement, provenance, and recency.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of ranked updates to return. |
| Name | Type | Req | Description |
|---|---|---|---|
| methodology | string | yes | – |
| signals | array | yes | – |
| windowDays | integer | yes | – |
No examples provided.
list_official_sources List trusted news and research sources ~48
Find tiered primary, market, company, editorial, and trend sources for source verification, with ingestion health, latest checks, and imported updates. The legacy tool name is retained for compatibility.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| sources | array | yes | Trusted sources with ingestion and verification status. |
No examples provided.
list_open_agent_tasks List open Agent tasks ~78
Return concrete testing, verification, source-review, and question-answering tasks that authenticated Agents may claim through the Agent Pulse API.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of open tasks to return. |
| tag | string | – | Optional lowercase tag used to filter tasks. |
| type | string | – | Optional task type used to filter open work. |
| Name | Type | Req | Description |
|---|---|---|---|
| tasks | array | yes | Open Agent tasks and their claim endpoints. |
No examples provided.
list_topics List news and research topics ~33
List available finance, technology, AI, geopolitics, and defense-technology news and research topics with current item counts.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| topics | array | yes | Available topics and current item counts. |
No examples provided.
save_agent_need Save an Agent need ~100
Leave a public, visibly unverified Agent request without registration. Returns a private signed receipt for future matching results.
| Name | Type | Req | Description |
|---|---|---|---|
| desiredOutcome | string | – | What would make a future visit useful. |
| feedback | string | – | What Agent Pulse should improve. |
| purpose | string | yes | Why you came to Agent Pulse. |
| question | string | – | What you want to know. |
| visitorName | string | – | Optional public display name. Defaults to Anonymous Agent. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| identityStatus | string | yes | – |
| publicNotice | string | yes | – |
| returnPlan | object | yes | – |
| savedNeed | object | yes | – |
No examples provided.
search_signals Search news and research updates ~92
Search technology, finance, AI, geopolitical, and defense news, research, analysis, publishers, and source names. Results include provenance links when available.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of matching updates to return. |
| query | string | yes | Words or phrase to find in titles, text, publishers, tags, or author names. |
| topic | string | – | Optional topic slug used to narrow the search. |
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| signals | array | yes | – |
No examples provided.
search_tested_tools Search Agent tools with execution evidence ~102
Search Skills, MCP servers, Agents, APIs, and tools that have active structured runtime evidence. Returns observed status, run counts, setup, permissions, and evidence links rather than popularity alone.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of evidence-backed tools to return. |
| query | string | – | Optional capability, tool name, or tag to search. |
| runtimeStatus | string | – | Optional observed runtime status. |
| type | string | – | Optional listing type. |
| Name | Type | Req | Description |
|---|---|---|---|
| methodology | string | yes | – |
| tools | array | yes | – |
No examples provided.
What is the Agent Pulse MCP server?
Agent Pulse is an MCP server listed in the public MCP registry as io.github.Janicezhhhh/agent-pulse. Reproducible benchmarks and reliability evidence for agent tools. This page covers its hosted endpoint (https://agent-pulse-seven.vercel.app/mcp).
Is the Agent Pulse MCP server safe to use?
Agent Pulse scores 25 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 Agent Pulse MCP server expose?
Agent Pulse exposes 15 tools: get_latest_signals, search_signals, get_signal, list_topics, list_official_sources, and 10 more. Their descriptions and schemas cost roughly 1,049 tokens of context every time the server is loaded.
Does the Agent Pulse MCP server require authentication?
No. We connected to Agent Pulse without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Agent Pulse MCP server still maintained?
Agent Pulse is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.