agentswitchboard

Name: agentswitchboard
Author: assafbar2

Server Details

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

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.

Status: Healthy
Uptime: 100.0% over 75 days
Last Tested: 2026-10-31 05:01
Transport: Streamable HTTP · MCP 2025-11-25
URL
Repository: assafbar2/agentswitchboard.dev
GitHub Stars: 0
Server Listing: agentSwitchBoard

TDQS

A3.7/5.0

Scored 2026-11-02 01:36 across 4 tools

Disambiguation4/5

The four tools map to clearly different operations: single-agent lookup by slug, filtered search, category enumeration, and a write-side submission. The only friction is description bleed — get_agent's description repeats the 'Featured ordering / relevance ranking' text that actually describes search_agents behavior, which could momentarily confuse an agent about which tool paginates/orders results.

Naming Consistency5/5

All four names follow a strict snake_case verb_noun pattern (get_agent, list_categories, search_agents, submit_listing). The verbs correctly signal read-single, read-collection, read-filtered, and write operations.

Tool Count4/5

Four tools is on the lean side but each one is load-bearing: discovery (search_agents), drill-down (get_agent), taxonomy (list_categories), and contribution (submit_listing). Nothing is redundant, though the surface is minimal enough that a few more read helpers could be justified.

Completeness4/5

Read coverage is solid — search, category browse, and full detail — and there is a write path for submissions. Gaps are minor but real: no way to check the status of a submission, no category-detail or featured/newest listing shortcut outside search, and no update/withdraw operation for a listing.

Available Tools

4 tools

get_agentGet Agent DetailsC

Read-onlyIdempotent

Inspect

Full detail for one agent by slug: skills, auth, streaming/push support, tags, provider 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. Featured: set only by the maintainer. With no search text, results list featured listings first, then A→Z; with search text, results are ranked by relevance and equal scores keep that featured-first order.

Name	Required	Description	Default
`slug`	Yes	Agent slug, e.g. "playwright-mcp"

Output Schema

Name	Required	Description
`url`	Yes
`name`	Yes
`slug`	Yes
`tags`	Yes
`skills`	Yes
`addedAt`	No
`iconUrl`	Yes	Absolute URL of the listing's 128px PNG icon, served by Agent Switchboard; null when it has none
`agentUrl`	Yes
`authType`	Yes
`featured`	Yes	Featured: set only by the maintainer. With no search text, results list featured listings first, then A→Z; with search text, results are ranked by relevance and equal scores keep that featured-first order.
`official`	Yes	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.
`provider`	Yes
`verified`	Yes	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.
`categories`	Yes
`description`	Yes
`providerUrl`	Yes
`accessMethods`	Yes
`officialVendor`	Yes
`supportsStreaming`	Yes
`supportsPushNotifications`	Yes

TDQS

C2.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds real value by decoding the 'Verified' and 'Official' labels an agent will encounter in the response, but it wastes the remaining space on featured-ordering mechanics that do not apply to a single-agent fetch.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The useful clause is one sentence at the front; the remainder is a glossary of Verified/Official/Featured and a paragraph on sort order ('featured listings first, then A→Z', 'ranked by relevance') that is entirely irrelevant to fetching one record. Roughly half the text does not earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema, rich annotations and a single fully documented parameter, little is strictly required, and the label glossary is a genuine aid to interpreting results. But the description says nothing about what happens when the slug is unknown or ambiguous, and closes on ordering rules that are simply wrong for this operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single slug parameter is documented with an example, so the schema carries the load. The description only echoes 'by slug' without adding matching rules or error behavior for an unknown slug. A 3 is the correct baseline when the schema already does this work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource: full detail for one agent, identified by slug, enumerating the fields returned (skills, auth, streaming/push support, tags, provider links). That clearly separates it from search_agents/list_categories by implication of single-record retrieval. It never explicitly names a sibling, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this versus search_agents (e.g. 'use after search to get full detail' or 'requires an exact slug, no fuzzy matching'). The only prescriptive content is about how listings are ordered when 'search text' is supplied — behavior that belongs to a search tool, not a get-by-slug lookup, and which misleads the reader about this tool's calling convention.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_categoriesList CategoriesA

Read-onlyIdempotent

Inspect

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

Name	Required	Description	Default
No parameters

Output Schema

Name	Required	Description
`categories`	Yes

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: counts are 'live' (freshness guarantee) and the returned slugs are consumable by a sibling tool. It does not discuss caching or ordering, but nothing essential is missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler. The core content (what is listed, what is included) is front-loaded and the downstream usage hint follows immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a full output schema and rich annotations, the description need not explain return shape or safety. It supplies the one thing structured fields cannot: that the counts are live and the slugs feed search_agents. Minor gap is no hint about ordering or whether all categories are always returned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters, so per the baseline this scores 4. The description still clarifies output semantics by noting the returned slugs are valid inputs elsewhere, which is useful framing rather than redundant schema restatement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (directory categories) plus a distinguishing attribute (live agent counts), so an agent can tell this apart from get_agent or search_agents. It is clear but the verb is only implied by the noun phrase, and no explicit 'list' framing is given.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Slugs are valid inputs for search_agents' tells the agent exactly what to do with the output, which effectively positions this as the discovery step before searching. There are no explicit exclusions or when-not-to-use conditions, but for a zero-parameter enumeration tool the routing intent is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_agentsSearch AgentsA

Read-onlyIdempotent

Inspect

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. Featured: set only by the maintainer. With no search text, results list featured listings first, then A→Z; with search text, results are ranked by relevance and equal scores keep that featured-first order.

Name	Required	Description
`auth`	No	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
`sort`	No	Result order. relevance (default): best match first with search text; without it, best fit first for a task, else featured then A→Z. newest: most recently added first. skills: most skills first. name: A→Z
`task`	No	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
`limit`	No	Max results per page (1–50)
`query`	No	Free-text search over name, description, skills, categories, tags, and provider
`access`	No	Require ALL of these access methods: api, mcp, cli, browser-extension ("extension" is accepted as an alias of browser-extension)
`offset`	No	Number of results to skip, for pagination
`category`	No	Category slug, e.g. "code-devtools", "voice-messaging"
`official`	No	Only first-party listings from major vendors (e.g. Notion's own Notion MCP)
`verified`	No	Only Verified listings: checked to work, re-checked monthly

Output Schema

Name	Required	Description
`limit`	Yes
`total`	Yes	Total matches before paging
`agents`	Yes
`offset`	Yes

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds genuinely non-obvious semantics: what 'Verified' means and that it is re-checked monthly and can drop, that 'Official' reflects publisher identity rather than paid placement, and that 'Featured' is maintainer-set. It does not discuss result volume, pagination limits, or rate limits, which is the remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and filter surface are front-loaded, which is good, but the 'Official' definition sprawls into a justification of vendor qualification (publicly traded, frontier lab, $1B+ valuation) that an agent does not need in order to call the tool. Roughly a third of the text is taxonomy explanation rather than invocation guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Ten optional parameters, all documented in the schema, and an output schema exists so return values need no prose. Combined with the description's coverage of filtering, ranking and the flag semantics, an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter including enum semantics and defaults. The description restates the filter set and the ranking order that the sort/query parameters already explain, adding little beyond the structured fields; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and a specific resource (the curated Agent Switchboard directory of AI agents, MCP servers, and agentic tools), with the filter/sort surface named up front. It is distinguishable from get_agent and list_categories by scope, though it never explicitly says how it relates to those siblings (e.g. 'use get_agent for full details of a result').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operational context: filtering dimensions, sort options, and what happens with and without search text (featured-first then A→Z vs relevance ranking). What is missing is explicit routing guidance — no when-not-to-use case and no pointer to get_agent for fetching a single listing's details.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

submit_listingSubmit a ListingAInspect

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.

Name	Required	Description
`url`	Yes	The product's own homepage, docs, or GitHub repo (https)
`name`	Yes	Product name, e.g. "Acme MCP"
`access`	No	How agents reach it: api, mcp, cli, browser-extension
`category`	No	Suggested category slug from list_categories
`description`	Yes	What it does and who it is for, in plain words (20–1500 characters)
`contact_email`	No	Optional. Sent privately to the maintainer for follow-up, never posted. Only include an address the user gave you for this purpose.

Output Schema

Name	Required	Description
`status`	Yes
`message`	Yes
`issueUrl`	No
`existingSlug`	No

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial context beyond the annotations: it discloses that the action creates a public GitHub issue rather than publishing, that a human reviews it, and gives concrete rate limits (5/hour per caller, one per URL per day). This resolves the mismatch an agent would otherwise infer between openWorldHint/readOnlyHint=false and the visible effect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences with zero filler; the effect ('opens a public issue, does not publish') is front-loaded before the conditional trigger and the rate limits.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists and annotations cover the safety profile, so the description only needs to cover effect, preconditions, and limits — all of which it does. Nothing an agent needs in order to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the schema. The description reinforces the three required fields in the user-confirmation step but adds no format or validation detail beyond that. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Suggest a new listing for the Agent Switchboard directory') and immediately scopes what that actually means ('opens a PUBLIC GitHub issue'). This is easily distinguished from siblings like search_agents or list_categories.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit trigger ('only when the user asks to submit or list a product'), an explicit prerequisite workflow (show the user the name, URL, and description and get agreement), and an explicit alternative ('Call search_agents first: if the product is already listed, tell the user instead').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

2 tool updatesOct 25, 2026

Changedget_agent4 fields changed

addedOutput schema / properties / featured

Added value: +{
+  "description": "Featured: set only by the maintainer. With no search text, results list featured listings first, then A→Z; with search text, results are ranked by relevance and equal scores keep that featured-first order.",
+  "type": "boolean"
+}

changedOutput schema / properties / official / description

Previous value: -"First-party listing from a major vendor"New value: +"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."

addedOutput schema / properties / verified / description

Added value: +"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."

changedOutput schema / required

Previous value: -[
-  "name",
-  "slug",
-  "description",
-  "provider",
-  "categories",
-  "accessMethods",
-  "authType",
-  "verified",
-  "official",
-  "officialVendor",
-  "url",
-  "agentUrl",
-  "providerUrl",
-  "skills",
-  "tags",
-  "supportsStreaming",
-  "supportsPushNotifications"
-]New value: +[
+  "name",
+  "slug",
+  "description",
+  "provider",
+  "categories",
+  "accessMethods",
+  "authType",
+  "verified",
+  "official",
+  "officialVendor",
+  "featured",
+  "url",
+  "agentUrl",
+  "providerUrl",
+  "skills",
+  "tags",
+  "supportsStreaming",
+  "supportsPushNotifications"
+]

Changedsearch_agents7 fields changed

changedInput schema / properties / access / description

Previous value: -"Require ALL of these access methods (api, mcp, cli, browser-extension)"New value: +"Require ALL of these access methods: api, mcp, cli, browser-extension (\"extension\" is accepted as an alias of browser-extension)"

changedInput schema / properties / access / items / enum

Previous value: -[
-  "api",
-  "mcp",
-  "cli",
-  "browser-extension"
-]New value: +[
+  "api",
+  "mcp",
+  "cli",
+  "browser-extension",
+  "extension"
+]

changedInput schema / properties / query / description

Previous value: -"Free-text search (name, description, skills, tags)"New value: +"Free-text search over name, description, skills, categories, tags, and provider"

addedOutput schema / properties / agents / items / properties / featured

Added value: +{
+  "description": "Featured: set only by the maintainer. With no search text, results list featured listings first, then A→Z; with search text, results are ranked by relevance and equal scores keep that featured-first order.",
+  "type": "boolean"
+}

changedOutput schema / properties / agents / items / properties / official / description

Previous value: -"First-party listing from a major vendor"New value: +"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."

addedOutput schema / properties / agents / items / properties / verified / description

Added value: +"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."

changedOutput schema / properties / agents / items / required

Previous value: -[
-  "name",
-  "slug",
-  "description",
-  "provider",
-  "categories",
-  "accessMethods",
-  "authType",
-  "verified",
-  "official",
-  "officialVendor",
-  "url"
-]New value: +[
+  "name",
+  "slug",
+  "description",
+  "provider",
+  "categories",
+  "accessMethods",
+  "authType",
+  "verified",
+  "official",
+  "officialVendor",
+  "featured",
+  "url"
+]

2 tool updatesOct 11, 2026

Changedget_agent3 fields changed

addedOutput schema / properties / official

Added value: +{
+  "description": "First-party listing from a major vendor",
+  "type": "boolean"
+}

addedOutput schema / properties / officialVendor

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "name",
-  "slug",
-  "description",
-  "provider",
-  "categories",
-  "accessMethods",
-  "authType",
-  "verified",
-  "url",
-  "agentUrl",
-  "providerUrl",
-  "skills",
-  "tags",
-  "supportsStreaming",
-  "supportsPushNotifications"
-]New value: +[
+  "name",
+  "slug",
+  "description",
+  "provider",
+  "categories",
+  "accessMethods",
+  "authType",
+  "verified",
+  "official",
+  "officialVendor",
+  "url",
+  "agentUrl",
+  "providerUrl",
+  "skills",
+  "tags",
+  "supportsStreaming",
+  "supportsPushNotifications"
+]

Changedsearch_agents4 fields changed

addedInput schema / properties / official

Added value: +{
+  "description": "Only first-party listings from major vendors (e.g. Notion's own Notion MCP)",
+  "type": "boolean"
+}

addedOutput schema / properties / agents / items / properties / official

Added value: +{
+  "description": "First-party listing from a major vendor",
+  "type": "boolean"
+}

addedOutput schema / properties / agents / items / properties / officialVendor
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```

changedOutput schema / properties / agents / items / required

Previous value: -[
-  "name",
-  "slug",
-  "description",
-  "provider",
-  "categories",
-  "accessMethods",
-  "authType",
-  "verified",
-  "url"
-]New value: +[
+  "name",
+  "slug",
+  "description",
+  "provider",
+  "categories",
+  "accessMethods",
+  "authType",
+  "verified",
+  "official",
+  "officialVendor",
+  "url"
+]

1 tool updateSep 18, 2026

Changedsearch_agents6 fields changed

addedInput schema / properties / limit / description
```
Added value: +"Max results per page (1–50)"
```

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Number of results to skip, for pagination",
+  "minimum": 0,
+  "type": "integer"
+}

addedOutput schema / properties / limit
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / offset
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / total / description
```
Added value: +"Total matches before paging"
```

changedOutput schema / required

Previous value: -[
-  "total",
-  "agents"
-]New value: +[
+  "total",
+  "offset",
+  "limit",
+  "agents"
+]

3 tool updatesSep 18, 2026

Changedget_agent1 field changed

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "accessMethods": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "addedAt": {
+      "type": "string"
+    },
+    "agentUrl": {
+      "type": "string"
+    },
+    "authType": {
+      "type": "string"
+    },
+    "categories": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "description": {
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    },
+    "provider": {
+      "type": "string"
+    },
+    "providerUrl": {
+      "type": "string"
+    },
+    "skills": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "description": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "name",
+          "description"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "slug": {
+      "type": "string"
+    },
+    "supportsPushNotifications": {
+      "type": "boolean"
+    },
+    "supportsStreaming": {
+      "type": "boolean"
+    },
+    "tags": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "url": {
+      "type": "string"
+    },
+    "verified": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "name",
+    "slug",
+    "description",
+    "provider",
+    "categories",
+    "accessMethods",
+    "authType",
+    "verified",
+    "url",
+    "agentUrl",
+    "providerUrl",
+    "skills",
+    "tags",
+    "supportsStreaming",
+    "supportsPushNotifications"
+  ],
+  "type": "object"
+}

Changedlist_categories1 field changed

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "categories": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "agentCount": {
+            "type": "number"
+          },
+          "description": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "slug": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "slug",
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "categories"
+  ],
+  "type": "object"
+}

Changedsearch_agents1 field changed

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "agents": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "accessMethods": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "authType": {
+            "type": "string"
+          },
+          "categories": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "description": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "provider": {
+            "type": "string"
+          },
+          "slug": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          },
+          "verified": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "name",
+          "slug",
+          "description",
+          "provider",
+          "categories",
+          "accessMethods",
+          "authType",
+          "verified",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "total",
+    "agents"
+  ],
+  "type": "object"
+}

3 tool updatesJul 24, 2026
- First observedget_agent
- First observedlist_categories
- First observedsearch_agents

Related MCP Connectors

AgentIndex A
app.agentindex
Search a curated directory of open-source AI agents, MCP servers and AI developer tools.
Search Developer Tools AI & Machine Learning
51
https://agentindex.app/api/mcp/
Bro Find AI A
com.brofindai
Search a curated directory of AI tools, AI agents and MCP servers by task, pricing and platform.
Search AI & Machine Learning
51
https://brofindai.com/api/mcp
AgentScout A
com.agentscouthq
Read-only search over 2,065+ AI agent tools and 276 MCP servers. Free, no sign-up needed.
Search Developer Tools
51
https://mcp.agentscouthq.com/mcp
AI Agents Listing B
io.github.nyyhao
Search, compare and find alternatives across a directory of AI agents, MCP servers and skills.
Search AI & Machine Learning Developer Tools
101
https://aiagentslisting.com/api/mcp

Related MCP Servers

beacon-mcp
AI & Machine Learning Developer Tools Search
enrichgateagent-png
A
license
A
quality
C
maintenance
MCP server that searches 3,800+ open-source AI agents by capability, ranked by real traction (stars, activity). Query it from Claude Desktop, Cursor, Cline, or Windsurf.
Updated 4 months ago (2026-07-13 17:16 UTC)
3
49 npm
MIT
mcp-harbor-search
Search Developer Tools
punkjazz-labs
A
license
A
quality
B
maintenance
A public, remote MCP server that lets AI agents search the MCP Harbor directory of 1,400+ MCP servers and AI-agent tools.
Updated 10 days ago (2026-10-23 08:26 UTC)
2
MIT
remoteopenclaw-mcp
Developer Tools Search
aidevelopers2
A
license
A
quality
F
maintenance
Enables AI agents to search a directory of 13,870+ MCP servers, 4,384+ agent skills, and plugins from Remote OpenClaw, returning install commands directly.
Updated 4 months ago (2026-07-02 11:15 UTC)
3
49 npm
6
MIT
PluginStack MCP Serverofficial
Developer Tools Documentation Access Search
pluginstackai
A
license
Not graded
quality
C
maintenance
Lets MCP clients such as Claude, Cursor, VS Code and Codex search a hand-checked directory of MCP servers, AI plugins and agent tools, returning summaries, copy-paste install configs and setup guides. Also supports keyword and category browsing plus troubleshooting guide lookups, working offline from a bundled snapshot when needed.
Updated 6 days ago (2026-10-27 23:57 UTC)
MIT