Deterministic research automation with live OpenAlex search and reusable workflow programs.
Scored across 8 tools
Each tool targets a distinct stage of a research automation pipeline (search, plan, compile, execute, preview, run, apply, diagnose), and the preview/run and compile/execute pairings are clearly differentiated by their descriptions. The preview_automation vs run_automation boundary is the only mild overlap, but the fingerprint-matching description clarifies it.
All tools follow a strict kata_ prefix plus verb_noun convention (kata_apply_command, kata_compile_workflow, kata_search_research), with no style mixing. The pattern is fully predictable.
Eight tools is well-scoped for a pipeline-oriented research automation server, with each tool covering a necessary stage. No redundant or filler tools are present.
The surface covers a coherent lifecycle: search, triage planning, compile, execute, preview, run, apply, and interop diagnosis. Minor gaps exist (e.g., no explicit workspace listing/status or automation removal), but core workflows are fully supported.
Apply one allowlisted semantic workspace command and return the next workspace snapshot.
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | ||
| workspace | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations already declaring idempotentHint=true and destructiveHint=false, the bar for additional disclosure is lower. The description adds meaningful context beyond annotations: it states that exactly one command is applied ('one allowlisted'), and that the tool returns a snapshot, giving the agent an expectation about the response shape and scope. It does not contradict the annotations and adds value by explaining the workspace-command interaction.
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, compact sentence with no filler. It front-loads the primary action ('Apply') and places the result at the end, making it easy to parse. Every word carries meaning, and there is no redundancy with the tool name 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?
For a tool with two nested object parameters, no output schema, and no parameter descriptions, the description leaves significant gaps: it does not define what a 'semantic workspace command' is, what 'allowlisted' means in practice, what fields are required in the workspace and command objects, or what the 'next workspace snapshot' contains. The idempotency annotation helps but does not resolve these operational unknowns. An agent would likely need to inspect examples or rely on sibling-tool patterns to invoke this correctly.
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 description coverage is 0%, so the description must compensate, but it only restates the parameter names in natural language: 'workspace' and 'command' appear as words in the description without explaining their structure or valid values. With two nested object parameters and no deeper schema properties, an agent cannot determine what a valid command object or workspace object looks like. The mention of 'allowlisted' hints at command constraints but does not specify allowed values or formats.
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 names a specific verb ('apply'), a defined resource ('one allowlisted semantic workspace command'), and states the outcome ('return the next workspace snapshot'). This is more specific than sibling names like kata_execute_program or kata_run_automation, clearly signaling a distinct action on a workspace state. It earns a full score because it distinguishes the tool without needing to open the schema.
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 gives no guidance on when to choose this tool over its siblings. It does not mention alternatives, exclusions, prerequisites, or a decision context such as 'use when you need to mutate workspace state via a allowlisted command.' The agent is left to infer that this is the command-application tool, but no explicit when/when-not guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compile two compatible semantic demonstrations into a deterministic JSON-Schema-constrained program.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| demos | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful behavioral context by describing the output as 'deterministic' and 'JSON-Schema-constrained', which suggests validation and a fixed structure. It does not, however, disclose what happens with incompatible demos, error behavior, or the exact form of the resulting program, so there is room for improvement.
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?
A single sentence that is front-loaded with the primary verb and noun phrase, and every word contributes meaning. It is compact, clear, and free of filler or redundant restatements of the tool name.
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 only two parameters and no output schema, the description must explain the full contract, but it does not. It does not describe the 'name' parameter, what 'demos' should look like, what the returned program is, or any error or validation behavior. The tool has readOnlyHint=true, so side effects are not a concern, but the overall invocation contract remains underspecified.
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 0% schema description coverage, the description must compensate for the schema's lack of parameter documentation. It adds some meaning to 'demos' by calling them 'two compatible semantic demonstrations', but it completely omits the 'name' parameter and does not clarify what the demos should contain or how compatibility is determined. This leaves a significant semantic gap.
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 clearly states the action ('Compile'), the input ('two compatible semantic demonstrations'), and the output ('a deterministic JSON-Schema-constrained program'). It is not a tautology and differentiates itself from siblings like kata_execute_program and kata_run_automation by indicating a compilation step rather than execution. However, 'semantic demonstrations' and 'program' remain somewhat abstract, so it loses one point for precision.
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?
No guidance is given about when to use this tool versus alternatives such as kata_plan_triage, kata_execute_program, or kata_run_automation. The description implies it should be used with two compatible demonstrations, but it never states conditions, exclusions, or when a sibling would be more appropriate. The agent is left to infer the intended workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Classify observed WebMCP, MCP, browser and API constraints and return a conservative compliant integration path without weakening security controls.
| Name | Required | Description | Default |
|---|---|---|---|
| intent | Yes | ||
| environment | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful context by promising a 'conservative compliant' path 'without weakening security controls', signalling the advisory, non-mutating nature of the output. It stops short of describing the actual returned structure or any limits/caveats of the classification.
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?
It is a single, front-loaded sentence with no filler, and the core action and output lead the text. However, the brevity is close to under-specification for a tool with such a rich input schema, so it is efficient rather than exemplary.
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?
There is no output schema, so partial explanation of the return value ('conservative compliant integration path') is acceptable, but the description gives no insight into the deeply nested, documentation-free environment object that dominates the input. For a tool of this apparent complexity, the definition is too thin to reliably guide correct invocation.
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 description coverage is 0%, and the description does not explain the 'intent' enum values or any of the roughly 23 nested 'environment' enums. Given that the single nested object carries the entire diagnostic input surface, the description should compensate but instead only alludes generally to 'observed constraints'. This leaves callers guessing at required field semantics.
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 names a specific verb pair (classify, return) and a clear resource domain (WebMCP, MCP, browser and API constraints), plus a distinct output ('conservative compliant integration path'). An agent can tell this is a diagnostic/advisory tool rather than an executor, though it never explicitly contrasts itself with siblings like kata_plan_triage or kata_run_automation.
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?
There is no statement of when to reach for this tool versus the many sibling tools, and no prerequisites or exclusions are given. The phrase 'observed ... constraints' implies the inputs must already be gathered, but that inference is left to the agent. No explicit when-to-use guidance is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a compiled deterministic program transactionally against a supplied workspace snapshot.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | ||
| program | Yes | ||
| workspace | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare idempotentHint=true and destructiveHint=false, but the description adds meaningful behavioral context: execution is transactional, the program is deterministic, and the execution acts on a supplied snapshot rather than a live workspace. This helps the agent understand isolation and repeatability beyond the structured annotations.
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, dense sentence with no filler. Every qualifier—'compiled,' 'deterministic,' 'transactionally,' 'supplied workspace snapshot'—adds meaning and is front-loaded for quick parsing.
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?
Despite clear purpose and behavioral qualifiers, the tool has three required nested object parameters with no schema descriptions and no output schema. The description does not explain expected parameter shapes, error behavior, return values, or side effects, so an agent would likely struggle to construct a correct invocation.
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 description coverage is 0%, so the description must compensate for the lack of parameter documentation. It clarifies that 'workspace' refers to a snapshot and hints that 'program' is a compiled deterministic program, but it does not explain the structure or role of 'input' or how the three nested objects relate. This is minimal compensation for three fully undocumented object parameters.
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 states a specific action ('Execute') on a specific resource ('compiled deterministic program') with a clear context ('against a supplied workspace snapshot'). It distinguishes this tool from siblings like kata_run_automation or kata_apply_command by emphasizing compiled, deterministic, transactional execution rather than interactive or command-based behavior.
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?
No guidance is given for when to use this tool versus alternatives. The description does not mention sibling tools, exclusions, prerequisites, or scenarios where another tool would be more appropriate. The qualifiers 'compiled deterministic program' and 'workspace snapshot' imply a narrow context, but the agent is left to infer usage rules.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a deterministic triage plan from live OpenAlex results or supplied works without mutating a workspace.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | ||
| works | No | ||
| actions | No | ||
| criteria | No | ||
| maxItems | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already provide readOnlyHint=true and openWorldHint=true, and the description goes beyond them by adding 'deterministic' and explicitly stating it does not mutate a workspace. It also names the external data source (live OpenAlex), which is useful behavioral context not present in the schema or annotations.
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, tightly written sentence that front-loads the core purpose and includes the most important constraint (non-mutation). Every word earns its place with no redundancy or filler.
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?
Despite the tool having six optional parameters, nested objects, no output schema, and open-world hints, the description provides only a high-level orientation. It does not explain return values, the meaning of triage actions/criteria, or the relationship between limit and maxItems, so an agent would still struggle to construct a correct invocation.
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 description coverage is 0%, so the description must compensate, but it only loosely maps 'query'/'works' to 'live OpenAlex results or supplied works'. The meanings of 'actions', 'criteria', 'limit', and 'maxItems' are not clarified, leaving several parameters semantically opaque for an agent.
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 specific verb ('Create') and names a concrete resource ('deterministic triage plan') with clear sources ('live OpenAlex results or supplied works'). It also states a key differentiator: the operation does not mutate a workspace, which helps distinguish it from execution-oriented sibling tools.
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 implies usage by naming two input sources and noting non-mutation, but it does not explicitly say when to choose this tool over siblings like kata_search_research or kata_run_automation. There is no stated when-not-to-use guidance or alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Preview an automation and return matching works plus an integrity fingerprint. Makes no changes.
| Name | Required | Description | Default |
|---|---|---|---|
| works | Yes | ||
| workspace | Yes | ||
| automation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so 'Makes no changes' reinforces that rather than adding new information. However, the description adds useful behavioral context about the output contract ('matching works plus an integrity fingerprint'), which goes beyond what annotations convey.
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 short sentences with no filler. The core action is front-loaded, and the safety guarantee is stated immediately, making the description easy to scan and understand.
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 lack of an output schema and the 0% schema description coverage, the description provides the essential purpose and output but leaves input object shapes undefined. An agent may not know what to supply for 'workspace' or what an 'integrity fingerprint' represents without additional domain knowledge.
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 description coverage is 0%, so the description must carry the burden of explaining the parameters. It hints that 'works' are the items being matched and 'automation' is the preview target, but the 'workspace' parameter is entirely unexplained, and the nested object structures remain opaque.
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 specific verb ('Preview') with a clear resource ('an automation') and states the result ('matching works plus an integrity fingerprint'). 'Makes no changes' distinguishes it from the sibling kata_run_automation, making the tool's role immediately clear.
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 safety cue 'Makes no changes' implies use for non-destructive previews, but the description never explicitly says when to choose this tool over alternatives like kata_run_automation. No exclusions or if-then conditions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a deterministic automation only when its preview fingerprint still matches current inputs. Nested tools are depth-bounded.
| Name | Required | Description | Default |
|---|---|---|---|
| works | Yes | ||
| workspace | Yes | ||
| automation | Yes | ||
| previewFingerprint | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, but say nothing about execution semantics. The description adds genuine behavioral traits beyond the annotations: the execution is deterministic, it is guarded by a fingerprint match to prevent stale-input runs, and nested tool calls are depth-bounded. No contradiction with the annotations.
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 with no filler: the first front-loads the action and guard condition, the second adds a nesting constraint. The phrase 'depth-bounded' is slightly vague (no actual limit given), but the sentence still earns its place as a behavioral warning about recursion.
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?
With no output schema, 0% parameter coverage, and four required parameters including two opaque objects (workspace, automation), the description leaves too much for the agent to infer. It doesn't say what happens when the fingerprint does not match, how to obtain the fingerprint, or what an 'automation' object should contain, despite kata_preview_automation being an obvious but unnamed prerequisite.
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 description coverage is 0%, so the description must carry the full burden of explaining parameters. It does give meaning to previewFingerprint — a fingerprint over current inputs that gates the run — and hints that 'current inputs' map to workspace/works. But workspace, works, and automation objects are entirely uncharacterized, leaving three of four required parameters unexplained.
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 specific verb-resource pair — 'Run a deterministic automation' — and adds a distinguishing guard condition ('only when its preview fingerprint still matches current inputs'). It implicitly contrasts with kata_preview_automation (preview vs. run), but never names the sibling, so differentiation is inferred rather than explicit.
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 states a hard precondition for invocation: the preview fingerprint must still match current inputs, which clearly implies a preview-then-run workflow. However, it never names kata_preview_automation as the required precursor, nor does it explain when to prefer alternatives like kata_execute_program. Usage context is present but the routing to alternatives is left implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search live scholarly works through OpenAlex. Returns normalized real research records; never mock data.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond the readOnlyHint and openWorldHint annotations by stating 'Returns normalized real research records; never mock data.' This tells the agent the output type and that data is live, not simulated. It does not contradict annotations.
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 entire description is one sentence, front-loaded with the purpose verb 'Search', and every clause adds value—'live', 'through OpenAlex', and 'never mock data' are all meaningful. There is no redundant or generic filler.
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 is brief but covers the core behavior, data source, and return type. With no output schema, 'normalized real research records' is slightly vague about fields or pagination, but for a two-parameter read-only search tool with clear annotations, this is largely sufficient.
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 description coverage is 0%, so the description must compensate. It implies that 'query' is the search term for scholarly works but says nothing about the optional 'limit' parameter. The schema's own type and bounds (integer 1-25) carry that meaning, so the description adds only marginal value for query and none for limit.
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 a specific verb and resource: 'Search live scholarly works through OpenAlex.' This clearly distinguishes the tool from its siblings (kata_apply_command, kata_execute_program, etc.), none of which perform scholarly search.
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 gives clear context for when the tool is appropriate: searching live scholarly works via OpenAlex. It doesn't explicitly state when not to use it or name alternatives, but the sibling set has no overlapping search tools, so the use case is unambiguous enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
kata_diagnose_web_interop12 fields changedInput schema / properties / environment / properties / authScopeAdded value: +{
+ "enum": [
+ "browser",
+ "all-paths",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / botProtectionScopeAdded value: +{
+ "enum": [
+ "browser",
+ "all-paths",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / crossOriginRequestAdded value: +{
+ "enum": [
+ "requested",
+ "not-requested",
+ "not-required",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / mcpAuthAdded value: +{
+ "enum": [
+ "none",
+ "required",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / mcpAuthMetadataAdded value: +{
+ "enum": [
+ "available",
+ "not-required",
+ "unverified",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / mcpEndpointAdded value: +{
+ "enum": [
+ "available",
+ "protected",
+ "legacy-candidate",
+ "unavailable",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / mcpModernProtocolAdded value: +{
+ "enum": [
+ "supported",
+ "unsupported",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / rateLimitScopeAdded value: +{
+ "enum": [
+ "browser",
+ "all-paths",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / environment / properties / serverSideApiAvailable / enumAdded value: +[
+ true,
+ false,
+ "unknown"
+]Input schema / properties / environment / properties / serverSideApiAvailable / typeRemoved value: -"boolean"Input schema / properties / environment / properties / termsScopeAdded value: +{
+ "enum": [
+ "browser",
+ "all-paths",
+ "unknown"
+ ],
+ "type": "string"
+}Input schema / properties / intent / enumPrevious value: -[
- "read",
- "act",
- "automate",
- "expose_webmcp",
- "call_api"
-]New value: +[
+ "read",
+ "act",
+ "automate",
+ "expose_webmcp",
+ "call_api",
+ "connect_mcp"
+]kata_apply_commandkata_compile_workflowkata_diagnose_web_interopkata_execute_programkata_plan_triagekata_preview_automationkata_run_automationkata_search_researchSearch arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Academic literature search, retrieval, and private library management on top of OpenAlex.
Search 250M+ research papers, citations and author profiles. Free OpenAlex account; OAuth sign-in.
Traceable scientific novelty and evidence assessment with source-linked results and a human gate.
Add one secure layer between your agents and this server.
