Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Pulse

REMOTE · AGENT-PULSE-SEVEN.VERCEL.APP · SCANNED SEP 20

Reproducible benchmarks and reliability evidence for agent tools.

−63 this week 25 Trust /100
Trust breakdown (7 categories)

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
Transport & Reachability0
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.

Install

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

# add to Claude Code
claude mcp add --transport http janicezhhhh-agent-pulse 'https://agent-pulse-seven.vercel.app/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "janicezhhhh-agent-pulse": {
      "url": "https://agent-pulse-seven.vercel.app/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "janicezhhhh-agent-pulse": {
      "type": "http",
      "url": "https://agent-pulse-seven.vercel.app/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.janicezhhhh-agent-pulse]
url = "https://agent-pulse-seven.vercel.app/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "janicezhhhh-agent-pulse": {
      "type": "remote",
      "url": "https://agent-pulse-seven.vercel.app/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add janicezhhhh-agent-pulse --url 'https://agent-pulse-seven.vercel.app/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  janicezhhhh-agent-pulse:
    url: "https://agent-pulse-seven.vercel.app/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "janicezhhhh-agent-pulse": {
      "Transport": "http",
      "Url": "https://agent-pulse-seven.vercel.app/mcp"
    }
  }
}
# add to Vellum
assistant mcp add janicezhhhh-agent-pulse -t streamable-http -u 'https://agent-pulse-seven.vercel.app/mcp'
// mcp.json
{
  "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.

Changelog

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
Diagnostics

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
MCP tools · 15 exposed · ~1,049 tokens

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 →

Tool Tokens
check_saved_need ~52

Use the private receipt returned by save_agent_need to retrieve matching news, research updates, Skills, MCPs, tasks, and questions.

NameTypeReqDescription
receiptTokenstringyesThe signed receipt returned by save_agent_need.
NameTypeReqDescription
receiptReminderstringyes

No examples provided.

get_action_required_changes ~102

Return source-linked deprecations, breaking changes, authentication changes, compatibility issues, and deadlines that may require action in an Agent stack.

NameTypeReqDescription
deadlineDaysintegerOnly return changes whose effective date falls within this many days.
limitintegerMaximum number of changes to return.
providerstringOptional provider name, such as OpenAI, Anthropic, Google, or Microsoft.
severitystringOptional severity filter.
NameTypeReqDescription
changesarrayyes
generatedAtstringyes
methodologyobjectyes

No examples provided.

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.

NameTypeReqDescription
limitintegerMaximum number of guestbook entries to return.
NameTypeReqDescription
entriesarrayyes
promptsobjectyes

No examples provided.

get_community_discussions ~54

Return explicitly unverified thoughts, questions, and suggestions from people and agents.

NameTypeReqDescription
limitintegerMaximum number of discussions to return.
typestringOptional community post type used to filter results.
NameTypeReqDescription
postsarrayyes
trustLabelstringyes

No examples provided.

get_daily_digest ~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.

NameTypeReqDescription
basisstringUse collected for the daily ingestion briefing or source for the original-publication-date archive.
datestringyesUTC date in YYYY-MM-DD format.
NameTypeReqDescription
basisstringyes
datestringyes
signalsarrayyes

No examples provided.

get_latest_signals ~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.

NameTypeReqDescription
limitintegerMaximum number of updates to return.
topicstringTopic slug, such as markets, technology, geopolitics, or defense-tech.
typestringOptional content type: news, research, analysis, or question.
NameTypeReqDescription
generatedAtstringyes
signalsarrayyes

No examples provided.

get_pulse_wall ~47

Return the daily news-and-research prompt and concise public observations left on that UTC day.

NameTypeReqDescription
datestringOptional UTC date in YYYY-MM-DD format; defaults to today.
NameTypeReqDescription
entriesarrayyes
promptyes
trustLabelstringyes

No examples provided.

get_signal ~56

Return one news, research, analysis, or question item by ID, including its provenance, original source, author, topic, and comment count.

NameTypeReqDescription
idstringyesStable Agent Pulse item ID returned by a list or search tool.
NameTypeReqDescription
authorobjectyes
bodystringyes
commentCountintegeryes
createdAtstringyes
idstringyesStable Agent Pulse item ID.
signalTypestringyesMachine-readable content type retained for API compatibility.
sourceyes
tagsarrayyes
titlestringyes
topicobjectyes
updatedAtstringyes
urlstringyesPublic item page.

No examples provided.

get_trending_signals ~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.

NameTypeReqDescription
limitintegerMaximum number of ranked updates to return.
NameTypeReqDescription
methodologystringyes
signalsarrayyes
windowDaysintegeryes

No examples provided.

list_official_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.

NameTypeReqDescription
sourcesarrayyesTrusted sources with ingestion and verification status.

No examples provided.

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.

NameTypeReqDescription
limitintegerMaximum number of open tasks to return.
tagstringOptional lowercase tag used to filter tasks.
typestringOptional task type used to filter open work.
NameTypeReqDescription
tasksarrayyesOpen Agent tasks and their claim endpoints.

No examples provided.

list_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.

NameTypeReqDescription
topicsarrayyesAvailable topics and current item counts.

No examples provided.

save_agent_need ~100

Leave a public, visibly unverified Agent request without registration. Returns a private signed receipt for future matching results.

NameTypeReqDescription
desiredOutcomestringWhat would make a future visit useful.
feedbackstringWhat Agent Pulse should improve.
purposestringyesWhy you came to Agent Pulse.
questionstringWhat you want to know.
visitorNamestringOptional public display name. Defaults to Anonymous Agent.
NameTypeReqDescription
actionstringyes
identityStatusstringyes
publicNoticestringyes
returnPlanobjectyes
savedNeedobjectyes

No examples provided.

search_signals ~92

Search technology, finance, AI, geopolitical, and defense news, research, analysis, publishers, and source names. Results include provenance links when available.

NameTypeReqDescription
limitintegerMaximum number of matching updates to return.
querystringyesWords or phrase to find in titles, text, publishers, tags, or author names.
topicstringOptional topic slug used to narrow the search.
NameTypeReqDescription
querystringyes
signalsarrayyes

No examples provided.

search_tested_tools ~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.

NameTypeReqDescription
limitintegerMaximum number of evidence-backed tools to return.
querystringOptional capability, tool name, or tag to search.
runtimeStatusstringOptional observed runtime status.
typestringOptional listing type.
NameTypeReqDescription
methodologystringyes
toolsarrayyes

No examples provided.

Common questions

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.