Kotlin Lib MCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kotlin Lib MCPfetch library io.ktor:ktor-client-core:latest"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
kotlin-lib-mcp
Give your AI agent the real sources of any Maven-published Kotlin/Java library.
An MCP server that, on request, downloads the sources of a
library (e.g. io.ktor:ktor-client-core:3.5.1), parses them with the Kotlin Analysis API
(standalone K2/FIR mode), and exposes structured information — public API surface, KDoc,
dependencies/metadata, raw source + search — to MCP clients such as Claude Code and Claude
Desktop. An optional Compose Desktop dashboard runs the same server in-process.


Why this and not a docs-lookup server?
Most documentation MCP servers scrape rendered doc sites or feed the model pre-digested summaries. This one works from the published sources jar — the ground truth:
Resolved signatures, not regex guesses. Declarations are analyzed with the same Analysis API that powers the Kotlin IDE, so
get_api_signaturereturns real, type-resolved signatures (with graceful best-effort fallback when transitive dependencies are missing).KMP-aware. Kotlin Multiplatform libraries publish per-target sources jars; these are resolved properly via
.moduleGradle metadata, and every symbol is tagged with its targets.KDoc as data. Summaries, descriptions and tags are extracted per declaration — not whole HTML pages.
Exact version you asked for, offline after the first fetch. Everything is cached on disk keyed by
group/artifact/version; no re-downloads, no drift between the docs and the version you actually depend on.Raw source when you need it.
get_sourceand boundedsearch_sourcelet the agent read the actual implementation, not just the API.
Related MCP server: codesurface
Quick start (no build required)
Option 1 — release zip. Download the latest release, unzip (needs a Java 21+ runtime), then:
claude mcp add kotlin-lib -- /path/to/kotlin-lib-mcp-server-<version>/bin/server --transport stdioOption 2 — Docker.
claude mcp add kotlin-lib -- docker run -i --rm -v kotlin-lib-mcp-cache:/home/mcp/.cache ghcr.io/aoreshkov/kotlin-lib-mcpOption 3 — MCP Registry. The server is published to the
official MCP registry as
io.github.aoreshkov/kotlin-lib-mcp; registry-aware clients can install it from there.
Or in .mcp.json / Claude Desktop config:
{
"mcpServers": {
"kotlin-lib": {
"command": "C:/path/to/kotlin-lib-mcp-server-<version>/bin/server.bat",
"args": ["--transport", "stdio"]
}
}
}For remote use, run the http transport (--transport http --port 3000) and point the client
at http://127.0.0.1:3000/mcp — DNS-rebinding protection admits localhost hosts by default;
--allowed-host/--allowed-origin extend the allowlist for non-localhost deployments.
CLI flags: --transport stdio|http, --port <int> (default 3000), --allowed-host <host> /
--allowed-origin <url> (repeatable; extend the http transport's localhost-only defaults),
--cache-dir <path>, --repo <url> (repeatable; Maven Central is the default),
--forward-logs-to-client (opt into mirroring logs to the client; off by default, stderr-only),
--otel (opt into OTLP/HTTP trace export; off by default — see Telemetry), --help.
Tools
All tools take a Maven coordinate (group:artifact:version). Call fetch_library first —
it downloads, extracts and analyzes the sources once; every other tool answers from the cached
index. fetch_library, list_versions and get_latest_version also accept group:artifact, and
fetch_library accepts group:artifact:latest to resolve the latest stable release.
Tool | Purpose |
| Download + analyze + cache; returns a summary. Idempotent. Version may be omitted or |
| Packages with declaration counts and KMP targets |
| Declarations with signatures; filter by |
| Resolved signature of one declaration by FQ name |
| KDoc (summary, description, tags) of one declaration |
| Raw source of a file ( |
| Substring/regex search; bounded, returns |
| Dependency tree from |
| Published versions from |
| Latest stable release (and newest overall) from |
Every tool ships the metadata the MCP spec encourages clients to use: a display title,
behavior annotations (readOnlyHint: true everywhere except fetch_library, which is
additive-only — destructiveHint: false, idempotentHint: true; tools that reach Maven
repositories set openWorldHint: true, cache-only tools false), a typed outputSchema
derived from the response DTO's serializer, and an icon. Results carry both pretty-printed JSON
text and the matching structuredContent object, so structured-output clients and plain-text
clients see the same payload.
fetch_library also reports progress notifications (download → analyze → cache) when the
client sends a progressToken. Logs go to stderr by default (which the spec blesses for all
stdio logging); the deprecated MCP logging capability — mirroring logs to clients as
notifications/message (respecting logging/setLevel) — is opt-in via --forward-logs-to-client,
for stdio clients that surface MCP log messages but drop stderr.
Elicitation
When fetch_library is called without a version (io.ktor:ktor-client-core, or …:latest) it has
to guess. If the client advertised the elicitation capability, it asks instead: an
elicitation/create form-mode request carrying a single-select version picker — the titled
oneOf shape from SEP-1330, with the latest stable release pre-selected as the schema default.
The user | The server |
accepts a version | fetches exactly that one |
declines | fetches the latest stable release, as it always did |
cancels (dismissed the dialog) | downloads nothing and returns a tool error saying to call |
There is no flag: capability negotiation is the opt-in. A client that advertises nothing — or advertises url-mode only, which servers must not answer with a form — keeps the previous silent latest-stable behavior exactly. Only public Maven version numbers are ever requested, so form mode is appropriate; URL mode exists for credentials and third-party authorization, and is deliberately unused here. Accepted values are validated against the offered list before they reach a repository URL, and a client that errors mid-question falls back to the default rather than failing the fetch.
Under --tasks, a task-augmented fetch_library parks in the input_required status while the
question is outstanding and returns to working once answered; the elicitation/create carries the
io.modelcontextprotocol/related-task _meta tying it to the task.
Note on concurrency. The Kotlin SDK's stdio transport processes one frame at a time and waits for each request handler to finish before reading the next, so a server-initiated request made from inside a tool call could never be answered — the reply would be stuck behind the very handler waiting for it. The stdio transport is therefore wrapped so that requests other than
initializeare dispatched concurrently, while notifications and responses stay inline and ordered. Besides making elicitation possible, this meansping,tasks/getandnotifications/cancelledare answered promptly during a longfetch_libraryinstead of queueing behind it.
Telemetry
Pass --otel to export a trace span for every MCP request (tools/call, resources/read,
prompts/get, completion/complete) over OTLP/HTTP. It is off by default, and off means
inert: no SDK, no exporter threads, no network.
Configuration is the standard OpenTelemetry environment surface — there are no bespoke flags:
export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 # '/v1/traces' is appended for you
export OTEL_SERVICE_NAME=kotlin-lib-mcp # this is also the default
export OTEL_RESOURCE_ATTRIBUTES=deployment.environment=dev
server --transport stdio --otelThe protocol defaults to http/protobuf, the endpoint to http://localhost:4318, and the
exporter uses the JDK's built-in HTTP client (no OkHttp on the classpath). Everything is
overridable: OTEL_EXPORTER_OTLP_HEADERS for a hosted collector's API key, OTEL_TRACES_EXPORTER,
OTEL_BSP_SCHEDULE_DELAY, and so on.
Endpoint gotcha. With the generic
OTEL_EXPORTER_OTLP_ENDPOINT,/v1/tracesis appended automatically. With the per-signalOTEL_EXPORTER_OTLP_TRACES_ENDPOINT, the URL is used as-is — you must spell out the path yourself. This is the most common OTLP misconfiguration.
Spans follow the MCP semantic conventions: named {method} {target} (e.g.
tools/call fetch_library), SpanKind.SERVER, and carrying mcp.method.name, gen_ai.tool.name,
mcp.session.id, and network.transport (pipe for stdio, tcp for http). A tool that returns
isError is marked error.type=tool_error. Inbound trace context is picked up from the JSON-RPC
params._meta bag (traceparent/tracestate, per SEP-414), so a client that traces
its own work gets one connected trace.
Those mcp.* and gen_ai.* attributes are still Development status upstream and may be
renamed — one more reason the whole feature is opt-in.
Resources: each cached library is readable at
kotlinlib://{group}/{artifact}/{version}/index (the parsed index as JSON); the list updates as
libraries are fetched, and the same URI shape is published as a resource template, so any
cached coordinate is directly addressable. Prompt: explain_public_api(coordinate, package?)
renders an explanation request grounded in the cached signatures and KDoc.
Icons: the server, every tool, the prompt and the library-index resource/template each declare
an SEP-973 icon, so a client can show the surface visually instead of as a wall of
snake_case. They are inlined as data: URIs rather than hosted URLs — a stdio server has no
origin, and the spec asks consumers to prefer same-origin icons and fetch them without credentials,
so inlining removes the third-party fetch entirely and keeps the icons working offline and inside
the container image. The payload is PNG, the one format icon-rendering clients must support
(image/svg+xml is only a SHOULD, and the spec warns it may carry executable content). The glyphs
are drawn by assets/icons/GenerateIcons.java and kept small —
about 800 bytes encoded each, since they ride in every tools/list.
Building from source
./gradlew build # build everything
./gradlew test # unit tests
./gradlew :server:run --args="--transport stdio" # local MCP over stdio (default)
./gradlew :server:run --args="--transport http --port 3000" # Streamable HTTP at /mcp
./gradlew :dashboard:run # Compose Desktop UI
./gradlew :server:installDist # standalone launcher in server/build/install/server/binRequires JDK 21 (resolved automatically via Gradle toolchains).
Module | What it is |
| KMP library: domain model + ports ( |
| JVM app: MCP tools/resources/prompts + stdio and Streamable HTTP transports |
| Compose Desktop control panel embedding the server (optional) |
Cache
Downloads and the parsed index live under the OS cache dir + kotlin-lib-mcp
(%LOCALAPPDATA%\kotlin-lib-mcp on Windows, ~/Library/Caches/kotlin-lib-mcp on macOS,
$XDG_CACHE_HOME/kotlin-lib-mcp elsewhere), keyed by group/artifact/version — browsable and
safe to delete. --cache-dir overrides it.
Notes
stdio rule: stdout carries only MCP protocol frames; all logging goes to stderr (Kermit → SLF4J → Logback,
logback.xml).Kotlin and the Analysis API artifacts are version-locked in
gradle/libs.versions.toml— bump them together. Symbols whose types can't be resolved (missing transitive deps) degrade tobestEffort: truePSI signatures instead of failing.
Contributing
Contributions welcome — see CONTRIBUTING.md. Release history lives in CHANGELOG.md; security reports go through private vulnerability reporting.
Support
If kotlin-lib-mcp saves you time, consider
sponsoring its maintenance. Sponsorship funds
keeping the Analysis API version-lock current with new Kotlin releases and the
supply-chain-hardened release pipeline. Every tier is appreciated.
License
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aoreshkov/kotlin-lib-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server