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.

io.github.assafbar2/agentswitchboard

REMOTE · AGENTSWITCHBOARD.DEV

Search a curated directory of 800+ AI agents, MCP servers, and agentic tools.

0 this week 79 Trust /100

Last scanned (20 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

Recent critical change

Authorization (4 Nov 2026). See the changelog before you install this server.

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 & Reachability100
Schema Quality & AI Usability64
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2239 tokens (~248/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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • 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 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 supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

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 →

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.

  • 15 Nov 26 0
    • Server version: 1.10.0 → 1.11.0 functional
  • 14 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 1748 → 2239 ▼ functional
    • Server version: 1.8.0 → 1.10.0 functional
    • New tool “recommend” functional
    • New tool “request_missing_tool” functional
  • 11 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 9 Nov 26 +1
    • Stability: 0.97 → pass security
  • 8 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 6 Nov 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
  • 4 Nov 26 +54
    • Authorization: unverified → fail ▼ critical
    • Injection markers: unverified → pass ▲ security
    • Stability: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_agent” rewrote its description, which is the text the model reads security
    • Tool “search_agents” rewrote its description, which is the text the model reads security
    • Tool “submit_listing” rewrote its description, which is the text the model reads security
    • Tool “submit_listing” is now declared destructive security
    • Endpoint reachability: not serving MCP → reachable ▲ functional
    • Schema quality: 278 → 249 ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Server version: 1.5.0 → 1.8.0 functional
    • New tool “alternatives_to” functional
    • New tool “compare_agents” functional
    • New tool “connect_bundle” functional
    • “search_agents” added an optional parameter “since” cosmetic
    • “search_agents” reworded the description of “query” cosmetic
    • “search_agents” reworded the description of “sort” cosmetic
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 21 Nov 2026 · Probed https://agentswitchboard.dev/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=agentswitchboard.dev CN=YR2,O=Let's Encrypt,C=US 2 Oct 2026 31 Dec 2026 RSA 2048 SHA256-RSA 56028a2227f22d50275ea5f860c00e45ec3
SANs: agentswitchboard.dev
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
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 agentswitchboard.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
agentswitchboard.dev. 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

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agentswitchboard.dev/api/mcp Verified 200
http (plaintext) http://agentswitchboard.dev/api/mcp HTTPS enforced 308 https://agentswitchboard.dev/api/mcp
MCP tools · 9 exposed · ~2,001 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
alternatives_to ~152

Listings that could stand in for one listing, strongest first, as on its /agents/<slug>/alternatives page. Each alternative is in the listing's main category, offers at least one of its access methods, and overlaps on what it does (shared skills and tags, rarer ones counting for more). Each comes with why: the access methods both offer and what they have in common. Up to 8. Fewer, or none, rather than a weak match. Also returns a link comparing the listing with its top two alternatives.

NameTypeReqDescription
limitinteger–Most alternatives to return (1–8, default 8)
slugstringyesAgent slug, e.g. "deepgram"
NameTypeReqDescription
agentobjectyes–
alternativesarrayyes–
basisstringyesWhat every alternative has in common with the listing
compareUrlstring|nullyesThe listing side by side with its top two alternatives
totalintegeryesHow many alternatives it has, up to 8
urlstring|nullyesIts alternatives page; null when it has too few for one

No examples provided.

compare_agents ~198

Put 2 or 3 listings side by side, as the site's /compare page does. For each listing: the facts that set it apart from the others ("Only one with a CLI", "No auth required", "Most skills (12)"). Then one row per field, with each listing's value by slug: what it is, provider, official vendor, verified, access, auth, MCP server, CLI install, API base URL, skills, streaming, push, categories, tags, listed since. A row where every listing agrees has same: true. Facts from the listings' own data, never a verdict. A curated comparison of the same listings adds its intro line. Unknown or repeated slugs, and any past 3, are left out with a note.

NameTypeReqDescription
slugsarrayyesListing slugs to compare, in column order: 2 or 3, e.g. ["deepgram", "assemblyai"]
NameTypeReqDescription
agentsarrayyes–
introstring|nullyesA curated comparison's editorial line; null for any other mix
notesarrayyesNamed listings that were left out, and why
rowsarrayyes–
titlestringyes–
urlstringyesThe comparison on the site

No examples provided.

connect_bundle ~193

One MCP client config to paste ({"mcpServers": …}, as Cursor and other MCP clients read it) for up to 10 listings, and how each one connects. A listing is in the config when its own docs give a hosted server address or a local command. An MCP server whose docs give neither comes with its setup guide, and setupPrompt asks a coding agent to set all of those up. A listing without an MCP server comes with its CLI install command, API address or docs. Also returns a claude mcp add command for each server in the config, for Claude Code, and the /stack link for the listings. Nothing is guessed: every address and command is copied from the vendor's docs, as on the listing's page.

NameTypeReqDescription
slugsarrayyesListing slugs, in the order to list them: 1 to 10, e.g. a stack's items
NameTypeReqDescription
claudeCodearrayyesA claude mcp add command for each server in the config
config–yesThe MCP client config to paste; null when no listing has an address or command to copy
itemsarrayyes–
notesarrayyesNamed listings that were left out, and why
setupPromptstring|nullyesFor a coding agent: set up each MCP server that has only a setup guide
stackUrlstringyesThese listings as a shared stack on the site
summarystringyesHow many are in the config, to set up from a guide, and without an MCP server

No examples provided.

get_agent ~194

Full detail for one agent by slug: skills, auth, streaming/push support, tags, provider links, and useItNow: how to start using it (MCP client config, install command, API base URL, setup links). Verified: we checked it works — its URLs load and its declared access (API, MCP, CLI or extension) responds. Re-checked monthly; the label drops if it stops working. Official: a first-party listing, published by the company behind the product under its own domain or GitHub org (e.g. Notion's own Notion MCP, not a community build), where that company is a major vendor (publicly traded, a frontier AI lab, or valued around $1B+). It records who publishes the product, not a paid placement, and is separate from Verified.

NameTypeReqDescription
slugstringyesAgent slug, e.g. "playwright-mcp"
NameTypeReqDescription
accessMethodsarrayyes–
addedAtstring––
agentUrlstringyes–
apiBaseUrlstring|nullyesBase URL of the vendor's public API
authTypestringyes–
categoriesarrayyes–
descriptionstringyes–
iconUrlstring|nullyesAbsolute URL of the listing's 128px PNG icon, served by Agent Switchboard; null when it has none
install–yesThe command that installs its CLI
mcpCommandstring|nullyesThe command that runs its MCP server locally
mcpEndpointstring|nullyesThe vendor's hosted MCP server address
namestringyes–
officialbooleanyesOfficial: a first-party listing, published by the company behind the product under its own domain or GitHub org (e.g. Notion's own Notion MCP, not a community build), where that company is a major ve…
officialVendorstring|nullyes–
providerstringyes–
providerUrlstringyes–
quickstartUrlstring|nullyesThe vendor's setup or getting-started page
skillsarrayyes–
slugstringyes–
supportsPushNotificationsbooleanyes–
supportsStreamingbooleanyes–
tagsarrayyes–
urlstringyes–
useItNowobjectyesHow to start using it, per access method: client config and install links for MCP, the install command for a CLI, base URL and auth for an API. Commands and addresses come from the vendor's own docs;…
verifiedbooleanyesVerified: we checked it works — its URLs load and its declared access (API, MCP, CLI or extension) responds. Re-checked monthly; the label drops if it stops working.

No examples provided.

list_categories ~25

All directory categories with live agent counts. Slugs are valid inputs for search_agents.

Input schema present but exposes no named parameters.

NameTypeReqDescription
categoriesarrayyes–

No examples provided.

recommend ~216

One recommendation for what your user needs, and the next step to start using it, as the site's Operator (/operator) picks it. Pass the need in a sentence you write yourself, e.g. "query Postgres and send email": each need it names gets one pick, why it fits, the next step (the MCP client config to paste when the vendor's docs give one, else its setup guide or docs) and two alternatives; two or more picks also come with a /stack link. Name a product to prefer the listings that mention it; say MCP, CLI, API, browser extension or official to narrow the pick. Picked by fixed matching rules, not a model, so the same need always gets the same answer. A need that matches no task is refused with the closest tasks. Never include names, email addresses or phone numbers.

NameTypeReqDescription
needstringyesWhat the user needs, in a sentence or two, e.g. "query Postgres and send email" (up to 300 characters are read)
NameTypeReqDescription
answerstringyesThe recommendations in plain sentences, one line per need, ready to tell the user
basisstringyesHow the pick is made
notesarrayyes–
operatorUrlstringyesThe same request on the site
recommendationsarrayyes–
requeststringyesThe need as read
stackUrlstring|nullyesTwo or more picks as a shared stack on the site
unmatchedarrayyesNeeds with no pick, and the tasks closest to them

No examples provided.

request_missing_tool ~219

Tell the Agent Switchboard maintainer that the directory has nothing for a job. Use it after search_agents (and a task or category, if one fits) found nothing that does what the user needs. The request is recorded privately and read in the weekly review, which uses requests to decide what to look for and add; nothing is published, no issue is opened, and there is no reply. Describe the job, never the user: no names, emails, company details or conversation. Limited to 10 requests per hour per caller.

NameTypeReqDescription
accessarray–How the agent needs to reach it: api, mcp, cli, browser-extension
categorystring–Closest category slug from list_categories, if any
needstringyesThe job no listing does, in plain words (10–500 characters), e.g. "an MCP server that files expense reports in Expensify". Describe the job, not the user.
triedstring–The search words that found nothing, if any
NameTypeReqDescription
messagestringyes–
statusstringyes–

No examples provided.

search_agents ~548

Search the curated Agent Switchboard directory of AI agents, MCP servers, and agentic tools. Filter by task, category slug, access methods, official (first-party listings from major vendors), verified, and/or auth type; sort by relevance, newest, most skills, or name. Verified: we checked it works — its URLs load and its declared access (API, MCP, CLI or extension) responds. Re-checked monthly; the label drops if it stops working. Official: a first-party listing, published by the company behind the product under its own domain or GitHub org (e.g. Notion's own Notion MCP, not a community build), where that company is a major vendor (publicly traded, a frontier AI lab, or valued around $1B+). It records who publishes the product, not a paid placement, and is separate from Verified.

NameTypeReqDescription
accessarray–Require ALL of these access methods: api, mcp, cli, browser-extension ("extension" is accepted as an alias of browser-extension)
autharray–Only listings with one of these auth types: none (no key or sign-in needed), apiKey, oauth2, bearer. A listing has one auth type, so several mean any of them
categorystring–Category slug, e.g. "code-devtools", "voice-messaging"
limitinteger–Max results per page (1–50)
officialboolean–Only first-party listings from major vendors (e.g. Notion's own Notion MCP)
offsetinteger–Number of results to skip, for pagination
querystring–Free-text search over name, description, skills, categories, tags, and provider (up to 200 characters; longer text is cut)
sincestring–Only listings added to the directory on or after this day: a date (YYYY-MM-DD), or a number of days back with today included ("7" is the last 7 days). Add sort "newest" to list the newest first
sortstring–Result order. relevance (default): best match first with search text; without it, best fit first for a task, else A→Z. newest: most recently added first. skills: most skills first. name: A→Z
taskstring–Task slug, e.g. "query-a-database": only the listings that do that job, best fit first. GET https://agentswitchboard.dev/api/tasks lists the tasks
verifiedboolean–Only Verified listings: checked to work, re-checked monthly
NameTypeReqDescription
agentsarrayyes–
limitintegeryes–
offsetintegeryes–
sincestring–With since: the first day kept (YYYY-MM-DD, UTC)
totalintegeryesTotal matches before paging

No examples provided.

submit_listing ~256

Suggest a new listing for the Agent Switchboard directory. This opens a PUBLIC GitHub issue that the maintainer reviews by hand; it does not publish anything. Use it only when the user asks to submit or list a product, after you show them the name, URL, and description you will send and they agree. Call search_agents first: if the product is already listed, tell the user instead. Limited to 5 submissions per hour per caller and one per URL per day. Not safe to retry blindly: each call that returns status "filed" opens a new issue.

NameTypeReqDescription
accessarray–How agents reach it: api, mcp, cli, browser-extension
categorystring–Suggested category slug from list_categories
contact_emailstring–Optional. Sent privately to the maintainer for follow-up, never posted. Only include an address the user gave you for this purpose.
descriptionstringyesWhat it does and who it is for, in plain words (20–1500 characters)
namestringyesProduct name, e.g. "Acme MCP"
urlstringyesThe product's own homepage, docs, or GitHub repo (https)
NameTypeReqDescription
existingSlugstring––
issueUrlstring––
messagestringyes–
statusstringyes–

No examples provided.

Install

How do I install the io.github.assafbar2/agentswitchboard MCP server?

io.github.assafbar2/agentswitchboard is a hosted endpoint at https://agentswitchboard.dev/api/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 · agentswitchboard.dev

# add to Claude Code
claude mcp add --transport http assafbar2-agentswitchboard 'https://agentswitchboard.dev/api/mcp'
Common questions

What is the io.github.assafbar2/agentswitchboard MCP server?

io.github.assafbar2/agentswitchboard is an MCP server listed in the public MCP registry as io.github.assafbar2/agentswitchboard. Search a curated directory of 800+ AI agents, MCP servers, and agentic tools. This page covers its hosted endpoint (https://agentswitchboard.dev/api/mcp).

Is the io.github.assafbar2/agentswitchboard MCP server safe to use?

io.github.assafbar2/agentswitchboard scores 79 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 io.github.assafbar2/agentswitchboard MCP server expose?

io.github.assafbar2/agentswitchboard exposes 9 tools: search_agents, get_agent, list_categories, compare_agents, alternatives_to, and 4 more. Their descriptions and schemas cost roughly 2,001 tokens of context every time the server is loaded.

Does the io.github.assafbar2/agentswitchboard MCP server require authentication?

No. We connected to io.github.assafbar2/agentswitchboard without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the io.github.assafbar2/agentswitchboard MCP server still maintained?

io.github.assafbar2/agentswitchboard 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 io.github.assafbar2/agentswitchboard MCP server?

VerifyMCP ran 13 checks on io.github.assafbar2/agentswitchboard, 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.