cyanheads-mcp-server
Server Details
Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.
- Status
- Healthy
- Uptime
- 99.9% over 41 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- cyanheads/cyanheads-mcp-server
- GitHub Stars
- 1
- Server Listing
- cyanheads-mcp-server
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one searches the catalog and the other retrieves detailed information for a specific entry. There is no overlap in their functionality.
Both tool names follow the same verb_noun pattern: 'cyanheads_describe_entry' and 'cyanheads_search_catalog'. The prefix 'cyanheads_' is consistent and the verbs 'describe' and 'search' clearly indicate their actions.
With only two tools, the server feels minimal, but the scope (discovering tools and servers) may not require more. It is borderline for a discovery-focused server, as these two tools likely cover the core needs of searching and retrieving details.
The domain appears to be catalog discovery and retrieval for MCP servers/tools. Search and describe cover the primary workflows; minor gaps like listing all entries or filtering by category are not covered but can be worked around.
Available Tools
2 toolscyanheads_describe_entryDescribe Fleet Tool or ServerARead-onlyInspect
Return the description and install snippets for a named tool or server. For tools: the description and the server it belongs to. For servers: local (stdio, via npx) install snippets for every published server, plus remote (HTTP) connection snippets when a hosted endpoint exists — for every supported client, or one client via the client parameter.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Whether name refers to a tool or server. Omit to auto-detect: names containing underscores are treated as tools; names containing hyphens are treated as servers. | |
| name | Yes | Tool name (snake_case, e.g. "earthquake_search") or server name (kebab-case, e.g. "earthquake-mcp-server"). 1-64 characters. Use cyanheads_search_catalog to discover valid names. | |
| client | No | Return install snippets for this client only (both local and remote transports when available). Omit to return snippets for all supported clients. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| result | No | The resolved entry — either a tool detail or a server detail depending on the resolved kind. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the description doesn't need to state that it's read-only. The description adds meaningful behavioral context beyond the schema: it explains that server install snippets include local (stdio via npx) for every published server and remote (HTTP) when a hosted endpoint exists, and how the `client` parameter influences output (one client vs all). There is no contradiction with annotations, and the openWorldHint=false is consistent with the enum-constrained `kind` and `client` parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured paragraph of three sentences that front-loads the core purpose, immediately explains the tool-vs-server distinction, and then details output variations. Every sentence earns its place; there is zero fluff or redundant restating of the title or annotations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (3 parameters, 2 enums, output schema present), the description is nearly complete: it covers purpose, scoping, and output shape. The only minor gap is that it doesn't spell out what exactly the 'description' field contains for a server or tool, but the output schema presumably covers return values. Since an output schema exists, the description doesn't need to explain return values in depth, so this is quite complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and includes detailed parameter descriptions, so the baseline is 3. The description adds value by elaborating on what the returned output contains per kind and client, and by explaining the auto-detection logic for `kind` (underscores vs hyphens) which reinforces and extends the schema description. It clearly maps the `client` parameter to the behavior of limiting output. This goes beyond the schema, warranting a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a clear verb-resource structure ('Return the description and install snippets') and explicitly distinguishes behavior for tools vs servers, which differentiates it from its only sibling tool (cyanheads_search_catalog, which discovers names). It is immediately clear what this tool does and what class of objects it operates on.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description and parameter schema provide explicit usage guidance: the `kind` parameter explains when to set it vs auto-detect, and the `name` parameter explicitly says to use cyanheads_search_catalog to discover valid names. This is an explicit when/alternative routing (sibling tool for discovery, this tool for retrieval) and clarifies optional vs required parameters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
cyanheads_search_catalogSearch Fleet Tools and ServersARead-onlyInspect
Search fleet tools and servers by natural-language description. Returns ranked matches with brief summaries and the server each tool belongs to. Use scope "servers" to find which server handles a workflow; use the default scope "tools" to find specific tools.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return (1-20). Default 5. | |
| query | Yes | Natural language search query. Describe what you want to accomplish, a workflow, or a capability area. 1-500 characters. | |
| scope | No | What to search. "tools" returns individual tool matches; "servers" returns server-level matches. | tools |
| category | No | Filter by catalog category. Omit to search all categories. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| scope | No | Scope that was searched. |
| notice | No | Guidance when no results matched — e.g. how to broaden the query or try a different scope. Absent on successful result pages. |
| results | No | Ranked matches, best first. |
| servers | No | Roll-up of distinct servers across the full match set, before the limit slice. Present only for scope "tools". Ordered by topScore desc (name-tiebroken); capped at 10. Use serversTotal to see how many distinct servers matched in total. |
| totalCount | No | Total relevant matches before the limit was applied. |
| serversTotal | No | Total distinct servers in the full match set (before the cap of 10 is applied). Present only when servers is present. |
| effectiveQuery | No | The query that was searched. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation readOnlyHint=true already discloses the read-only nature,REDUCING the burden. The description adds concrete behavior: returns ranked matches, includes summaries, and reports which server each tool belongs to. It also defines what the two scopes return. No contradiction with annotations. Not perfect because it doesn't hint at result limits or staleness, but the added value is solid.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose and key output featuresasi. The scope guidance is placed in the second sentence and earns its place. No filler or repetition of schema content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description gives enough for an agent to properly invoke the tool: it explains the two scopes)Skip, notes ranked results with summaries, and the output schema (marked present) covers return structure. The 'category' parameter is not mentioned but is self-explanatory in the schema, and the tool's moderate complexity doesn't require more.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema coverage, the baseline is 3. The description compensates by adding meaning to the 'scope' parameter (choose 'servers' for workflows, 'tools' for specifics), which is genuinely useful beyond the schema text. Other parameters (query, limit, category) are adequately covered by their schema descriptions, so no further elaboration needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with the verb 'Search' and the specific resource 'fleet tools and servers', immediately stating what it does. It also disambiguates from the sibling cyanheads_describe_entry by emphasizing natural-language description and ranked matches, making the purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit guidance on when to use each scope: 'use scope "servers" to find which server handles a workflow; use default "tools" to find specific tools.' This tells the agent exactly how to select scope. It doesn't explicitly state when NOT to use the tool (e.g., when you need full details of a known entry, use describe_entry), but the clear scope disambiguation compensates.
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 updates
- Changed
cyanheads_describe_entry6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "result" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `not_found`: No tool or server with the given name exists in the catalog. `ambiguous_kind`: Name matches both a tool and a server (collision in catalog). `catalog_empty`: Catalog has not finished loading. Other values are possible when a failure originates below the handler.", + "examples": [ + "not_found", + "ambiguous_kind", + "catalog_empty" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "result" -]
- Changed
cyanheads_search_catalog6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "scope", + "effectiveQuery", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `catalog_empty`: Catalog has not finished loading. Other values are possible when a failure originates below the handler.", + "examples": [ + "catalog_empty" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "scope", - "effectiveQuery", - "totalCount" -]
4 tool updates
- Removed
cyanheads_describe - Added
cyanheads_describe_entry - Removed
cyanheads_search - Added
cyanheads_search_catalog
1 tool update
- Changed
cyanheads_describe1 field changed- changed
Output schema / properties / result / oneOfPrevious value: -[ - { - "additionalProperties": false, - "description": "A resolved tool entry — its description and the server that owns it.", - "properties": { - "description": { - "description": "Brief description of what the tool does.", - "type": "string" - }, - "kind": { - "const": "tool", - "description": "Resolved as a tool entry.", - "type": "string" - }, - "name": { - "description": "Resolved name (as looked up).", - "type": "string" - }, - "server": { - "description": "Server package name that owns this tool.", - "type": "string" - } - }, - "required": [ - "kind", - "name", - "description", - "server" - ], - "type": "object" - }, - { - "additionalProperties": false, - "description": "A resolved server entry — metadata, optional hosted endpoint, and per-client install snippets.", - "properties": { - "auth": { - "description": "Auth requirement for the hosted deployment (currently always \"none\").", - "type": "string" - }, - "description": { - "description": "Brief description of what the server does.", - "type": "string" - }, - "displayName": { - "description": "Human-readable server label.", - "type": "string" - }, - "endpoint": { - "description": "Streamable HTTP endpoint for the hosted deployment. Absent for local-only (stdio) servers.", - "type": "string" - }, - "github": { - "description": "GitHub repository URL.", - "type": "string" - }, - "installSnippets": { - "description": "Install instructions: local (stdio) snippets for every server, plus remote (HTTP) snippets when an endpoint exists. Filtered to one client when input.client is set.", - "items": { - "additionalProperties": false, - "description": "A single install instruction entry.", - "properties": { - "client": { - "description": "MCP client this snippet targets.", - "enum": [ - "claude-code", - "codex", - "cursor", - "curl", - "gemini", - "streamable-http" - ], - "type": "string" - }, - "label": { - "description": "Human-readable install method label.", - "type": "string" - }, - "payload": { - "description": "Install payload (JSON fragment or CLI command).", - "type": "string" - }, - "transport": { - "description": "Transport this snippet installs — stdio (local) or http (remote).", - "enum": [ - "stdio", - "http" - ], - "type": "string" - } - }, - "required": [ - "client", - "transport", - "label", - "payload" - ], - "type": "object" - }, - "type": "array" - }, - "kind": { - "const": "server", - "description": "Resolved as a server entry.", - "type": "string" - }, - "name": { - "description": "Resolved name (as looked up).", - "type": "string" - }, - "npm": { - "description": "npm package name (e.g. \"@cyanheads/arxiv-mcp-server\"). Drives the local stdio snippets.", - "type": "string" - }, - "requiredEnvVars": { - "description": "Env var names the local (stdio) install requires (e.g. [\"MAILCHIMP_API_KEY\"]). Absent when none.", - "items": { - "type": "string" - }, - "type": "array" - }, - "toolCount": { - "description": "Number of tools exposed by this server.", - "type": "number" - }, - "version": { - "description": "Published version captured at fleet-generation time.", - "type": "string" - } - }, - "required": [ - "kind", - "name", - "displayName", - "description", - "version", - "npm", - "github", - "auth", - "toolCount", - "installSnippets" - ], - "type": "object" - } -]New value: +[ + { + "additionalProperties": false, + "description": "A resolved tool entry — its description and the server that owns it.", + "properties": { + "description": { + "description": "Brief description of what the tool does.", + "type": "string" + }, + "kind": { + "const": "tool", + "description": "Resolved as a tool entry.", + "type": "string" + }, + "name": { + "description": "Resolved name (as looked up).", + "type": "string" + }, + "server": { + "description": "Server package name that owns this tool.", + "type": "string" + } + }, + "required": [ + "kind", + "name", + "description", + "server" + ], + "type": "object" + }, + { + "additionalProperties": false, + "description": "A resolved server entry — metadata, optional hosted endpoint, and per-client install snippets.", + "properties": { + "auth": { + "description": "Auth requirement for the hosted deployment (currently always \"none\").", + "type": "string" + }, + "description": { + "description": "Brief description of what the server does.", + "type": "string" + }, + "displayName": { + "description": "Human-readable server label.", + "type": "string" + }, + "endpoint": { + "description": "Streamable HTTP endpoint for the hosted deployment. Absent for local-only (stdio) servers.", + "type": "string" + }, + "github": { + "description": "GitHub repository URL.", + "type": "string" + }, + "installSnippets": { + "description": "Install instructions: local (stdio) snippets for every server, plus remote (HTTP) snippets when an endpoint exists. Filtered to one client when input.client is set.", + "items": { + "additionalProperties": false, + "description": "A single install instruction entry.", + "properties": { + "client": { + "description": "MCP client this snippet targets.", + "enum": [ + "claude-code", + "codex", + "cursor", + "curl", + "gemini", + "streamable-http" + ], + "type": "string" + }, + "label": { + "description": "Human-readable install method label.", + "type": "string" + }, + "payload": { + "description": "Install payload (JSON fragment or CLI command).", + "type": "string" + }, + "transport": { + "description": "Transport this snippet installs — stdio (local) or http (remote).", + "enum": [ + "stdio", + "http" + ], + "type": "string" + } + }, + "required": [ + "client", + "transport", + "label", + "payload" + ], + "type": "object" + }, + "type": "array" + }, + "kind": { + "const": "server", + "description": "Resolved as a server entry.", + "type": "string" + }, + "name": { + "description": "Resolved name (as looked up).", + "type": "string" + }, + "npm": { + "description": "npm package name (e.g. \"@cyanheads/arxiv-mcp-server\"). Drives the local stdio snippets.", + "type": "string" + }, + "requiredEnvVars": { + "description": "Env var names the local (stdio) install requires (e.g. [\"MAILCHIMP_API_KEY\"]). Absent when none.", + "items": { + "type": "string" + }, + "type": "array" + }, + "toolCount": { + "description": "Number of tools exposed by this server.", + "type": "number" + }, + "tools": { + "description": "Every tool this server exposes, each with its name and a brief description — one describe call reveals the full surface without a second lookup.", + "items": { + "additionalProperties": false, + "description": "A single tool exposed by this server.", + "properties": { + "description": { + "description": "Brief description of what the tool does.", + "type": "string" + }, + "name": { + "description": "Tool name (snake_case, e.g. \"earthquake_search\").", + "type": "string" + } + }, + "required": [ + "name", + "description" + ], + "type": "object" + }, + "type": "array" + }, + "version": { + "description": "Published version captured at fleet-generation time.", + "type": "string" + } + }, + "required": [ + "kind", + "name", + "displayName", + "description", + "version", + "npm", + "github", + "auth", + "toolCount", + "tools", + "installSnippets" + ], + "type": "object" + } +]
1 tool update
- Changed
cyanheads_describe2 fields changed- changed
Input schema / properties / client / descriptionPrevious value: -"Return the install snippet for this specific client only. Omit to return snippets for all supported clients."New value: +"Return install snippets for this client only (both local and remote transports when available). Omit to return snippets for all supported clients." - changed
Output schema / properties / result / oneOfPrevious value: -[ - { - "additionalProperties": false, - "properties": { - "description": { - "description": "Brief description of what the tool does.", - "type": "string" - }, - "kind": { - "const": "tool", - "description": "Resolved as a tool entry.", - "type": "string" - }, - "name": { - "description": "Resolved name (as looked up).", - "type": "string" - }, - "server": { - "description": "Server package name that owns this tool.", - "type": "string" - } - }, - "required": [ - "kind", - "name", - "description", - "server" - ], - "type": "object" - }, - { - "additionalProperties": false, - "properties": { - "auth": { - "description": "Auth requirement for the hosted deployment (currently always \"none\").", - "type": "string" - }, - "description": { - "description": "Brief description of what the server does.", - "type": "string" - }, - "displayName": { - "description": "Human-readable server label.", - "type": "string" - }, - "endpoint": { - "description": "Streamable HTTP endpoint for the hosted deployment.", - "type": "string" - }, - "github": { - "description": "GitHub repository URL.", - "type": "string" - }, - "installSnippets": { - "description": "Install instructions, one per supported client (or filtered by input.client).", - "items": { - "additionalProperties": false, - "description": "A single install instruction entry.", - "properties": { - "client": { - "description": "MCP client this snippet targets.", - "enum": [ - "claude-code", - "codex", - "cursor", - "curl", - "gemini", - "streamable-http" - ], - "type": "string" - }, - "label": { - "description": "Human-readable install method label.", - "type": "string" - }, - "payload": { - "description": "Install payload (JSON fragment or CLI command).", - "type": "string" - } - }, - "required": [ - "client", - "label", - "payload" - ], - "type": "object" - }, - "type": "array" - }, - "kind": { - "const": "server", - "description": "Resolved as a server entry.", - "type": "string" - }, - "name": { - "description": "Resolved name (as looked up).", - "type": "string" - }, - "npm": { - "description": "npm package name (e.g. \"@cyanheads/arxiv-mcp-server\").", - "type": "string" - }, - "toolCount": { - "description": "Number of tools exposed by this server.", - "type": "number" - }, - "version": { - "description": "Published version captured at fleet-generation time.", - "type": "string" - } - }, - "required": [ - "kind", - "name", - "displayName", - "description", - "version", - "npm", - "github", - "endpoint", - "auth", - "toolCount", - "installSnippets" - ], - "type": "object" - } -]New value: +[ + { + "additionalProperties": false, + "description": "A resolved tool entry — its description and the server that owns it.", + "properties": { + "description": { + "description": "Brief description of what the tool does.", + "type": "string" + }, + "kind": { + "const": "tool", + "description": "Resolved as a tool entry.", + "type": "string" + }, + "name": { + "description": "Resolved name (as looked up).", + "type": "string" + }, + "server": { + "description": "Server package name that owns this tool.", + "type": "string" + } + }, + "required": [ + "kind", + "name", + "description", + "server" + ], + "type": "object" + }, + { + "additionalProperties": false, + "description": "A resolved server entry — metadata, optional hosted endpoint, and per-client install snippets.", + "properties": { + "auth": { + "description": "Auth requirement for the hosted deployment (currently always \"none\").", + "type": "string" + }, + "description": { + "description": "Brief description of what the server does.", + "type": "string" + }, + "displayName": { + "description": "Human-readable server label.", + "type": "string" + }, + "endpoint": { + "description": "Streamable HTTP endpoint for the hosted deployment. Absent for local-only (stdio) servers.", + "type": "string" + }, + "github": { + "description": "GitHub repository URL.", + "type": "string" + }, + "installSnippets": { + "description": "Install instructions: local (stdio) snippets for every server, plus remote (HTTP) snippets when an endpoint exists. Filtered to one client when input.client is set.", + "items": { + "additionalProperties": false, + "description": "A single install instruction entry.", + "properties": { + "client": { + "description": "MCP client this snippet targets.", + "enum": [ + "claude-code", + "codex", + "cursor", + "curl", + "gemini", + "streamable-http" + ], + "type": "string" + }, + "label": { + "description": "Human-readable install method label.", + "type": "string" + }, + "payload": { + "description": "Install payload (JSON fragment or CLI command).", + "type": "string" + }, + "transport": { + "description": "Transport this snippet installs — stdio (local) or http (remote).", + "enum": [ + "stdio", + "http" + ], + "type": "string" + } + }, + "required": [ + "client", + "transport", + "label", + "payload" + ], + "type": "object" + }, + "type": "array" + }, + "kind": { + "const": "server", + "description": "Resolved as a server entry.", + "type": "string" + }, + "name": { + "description": "Resolved name (as looked up).", + "type": "string" + }, + "npm": { + "description": "npm package name (e.g. \"@cyanheads/arxiv-mcp-server\"). Drives the local stdio snippets.", + "type": "string" + }, + "requiredEnvVars": { + "description": "Env var names the local (stdio) install requires (e.g. [\"MAILCHIMP_API_KEY\"]). Absent when none.", + "items": { + "type": "string" + }, + "type": "array" + }, + "toolCount": { + "description": "Number of tools exposed by this server.", + "type": "number" + }, + "version": { + "description": "Published version captured at fleet-generation time.", + "type": "string" + } + }, + "required": [ + "kind", + "name", + "displayName", + "description", + "version", + "npm", + "github", + "auth", + "toolCount", + "installSnippets" + ], + "type": "object" + } +]
1 tool update
- Changed
cyanheads_search2 fields changed- added
Output schema / properties / serversAdded value: +{ + "description": "Roll-up of distinct servers across the full match set, before the limit slice. Present only for scope \"tools\". Ordered by topScore desc (name-tiebroken); capped at 10. Use serversTotal to see how many distinct servers matched in total.", + "items": { + "additionalProperties": false, + "description": "A server roll-up entry.", + "properties": { + "brief": { + "description": "One-line description of what the server does.", + "type": "string" + }, + "category": { + "description": "Catalog category.", + "enum": [ + "research", + "government", + "public-data", + "utility" + ], + "type": "string" + }, + "matchedTools": { + "description": "Count of this server's tools in the full match set.", + "type": "number" + }, + "name": { + "description": "Server package name (e.g. \"cdc-health-mcp-server\").", + "type": "string" + }, + "topScore": { + "description": "Best cosine similarity among this server's matched tools. Drives ordering. Distinct from the score a server gets under scope \"servers\".", + "type": "number" + } + }, + "required": [ + "name", + "brief", + "category", + "matchedTools", + "topScore" + ], + "type": "object" + }, + "type": "array" +} - added
Output schema / properties / serversTotalAdded value: +{ + "description": "Total distinct servers in the full match set (before the cap of 10 is applied). Present only when servers is present.", + "type": "number" +}
1 tool update
- Changed
cyanheads_search6 fields changed- added
Output schema / properties / effectiveQueryAdded value: +{ + "description": "The query that was searched.", + "type": "string" +} - added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no results matched — e.g. how to broaden the query or try a different scope. Absent on successful result pages.", + "type": "string" +} - removed
Output schema / properties / queryRemoved value: -{ - "description": "The query that was searched.", - "type": "string" -} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total relevant matches before the limit was applied.", + "type": "number" +} - removed
Output schema / properties / totalMatchedRemoved value: -{ - "description": "Total relevant matches before the limit was applied.", - "type": "number" -} - changed
Output schema / requiredPrevious value: -[ - "results", - "totalMatched", - "query", - "scope" -]New value: +[ + "results", + "scope", + "effectiveQuery", + "totalCount" +]
2 tool updates
- First observed
cyanheads_describe - First observed
cyanheads_search
Related MCP Connectors
Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client.
MCP registry & directory: search, find & install 31k+ MCP servers & tools. Catalog and marketplace.
Search and get install details on MCP servers, right from your agent -- a unified marketplace index.
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAI-first MCP server discovery tool that enables agents to search, inspect, and install MCP servers from multiple registries.12AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables MCP-based hybrid semantic code search over repositories, providing tools for searching code by meaning or keyword, retrieving symbol definitions, finding usages, reading chunks, and listing indexed repos.MIT
- AlicenseNot gradedqualityAmaintenanceEnables semantic code search across repositories via MCP, returning exact source excerpts with paths and line numbers.207 npm62MIT
- AlicenseAqualityDmaintenanceLocal-first MCP server for semantic + keyword hybrid code search. Zero external services, no API keys required.2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.