mcpserverlist-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_SERVER_LIST_URL | No | Remote MCP endpoint URL. | https://mcpserverlist.io/mcp |
| MCP_SERVER_LIST_API_KEY | No | API key sent as `Authorization: Bearer <key>`. Only sent when set. Required only for tools that act on your account; discovery and check tools work without it. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_directoriesA | Anonymous catalog with source references and requirements. Discovery does not establish purchase eligibility; run a full authenticated preflight. |
| check_repositoryA | Anonymous free diagnostic for a public GitHub repository. This is not the per-destination purchase preflight. |
| create_accountB | Anonymous signup returns a new account API key once. Save it securely; email is not an access or recovery credential. |
| get_accountA | Requires API key. Read account and configured billing/execution availability. Generic launch credits are not sold. |
| connection_instructionsA | Read-only instructions for direct HTTPS credential upload. Never put third-party secrets in chat or MCP tool arguments. |
| list_connectionsA | Requires API key. Returns owned connection IDs, providers, expiry and revocation metadata. Never returns plaintext or ciphertext. |
| revoke_connectionB | Requires explicit owner authorization. Revoking a connection prevents jobs using it from completing until reconnected. |
| list_serversB | Requires API key; returns only your saved profiles. |
| create_serverB | Requires API key. Save accurate public profile fields before checking all selected destination prerequisites. Smithery currently needs a public unauthenticated Streamable HTTP endpoint and owned namespace/server name. |
| import_repositoryB | Inspect a public repository and save an owned launch intake. Infers evidenced public facts and asks only missing facts. No upstream writes or payment. |
| get_launch_intakeB | Read your persisted profile, evidence, missing questions and next action. |
| answer_launch_questionsC | Save explicit public answers to the questions in an owned intake. No upstream mutation or payment. |
| check_launch_coverageB | Check all implemented destinations with read-only provider requests, remove blocked destinations and preserve prerequisites. Saves the exact final report. Six direct submissions minimum; no charge or upstream writes. |
| prepare_repositoryB | Free owner-authenticated inspection at a pinned GitHub revision. Returns exact proposed file diffs, preservation warnings and approval digest. No external writes. |
| get_repository_preparationB | Read owned pinned patch, warnings and digest before authorizing a PR within existing owner authority or requesting missing approval. |
| create_preparation_pull_requestA | Requires explicit owner approval of the exact displayed patch digest. Creates a branch and PR in the source repository, never merges or publishes. After uncertain writes, only reconciles matching existing PRs; never blindly retries writes. |
| create_publisher_taskB | Free preparation for Claude/OpenAI owner review. Saves a field packet and eligible package; never submits, proves delivery or adds paid coverage. No secrets or credential uploads. |
| list_publisher_tasksB | Read owned preparation tasks and operator journal status; pending provider work is not fulfillment. |
| get_publisher_taskA | Read the exact owned task revision, digest, missing owner/provider actions and optional authenticated ZIP download link. No raw binary or credentials are returned through MCP. |
| authorize_publisher_taskA | Only use within existing explicit owner authority covering this exact task revision, digest, submit/publish action and truthful attestations; obtain missing authority first. Records a guarded grant, not proof of submission, approval or publication. Does not pay. |
| run_preflightC | Requires API key. Read-only provider checks produce an immutable 30-minute report, exact public payloads, blockers and remedies. No external submission or charge occurs. Unsupported/paused destinations cannot be bought. |
| get_preflightB | Requires API key. Review every target, blocker and proposed public payload with the owner before authorizing a paid launch. |
| create_launchA | Requires API key and explicit owner authorization of the displayed preflight plans. Creates an unpaid draft bound to a ready owned preflight; this call does not pay. Verified payment later automatically queues the authorized submissions. |
| payment_instructionsA | Read-only protocol instructions for an approved launch_id. No payment is made by this tool. Obtain owner authorization for the saved launch amount (current new-launch offer $99); payment starts automatic submissions. |
| create_checkoutB | Requires API key, launch ID and stable purchase key. Human payment fallback for the saved immutable service fee (current new-launch offer $99); only verified paid settlement queues jobs. This tool does not autonomously pay. |
| list_service_casesC | Read owned delivery reviews, assigned operator, due date and fulfillment summary. |
| get_service_caseB | Read an owned review with operator updates and resolution evidence. |
| reply_to_service_caseB | Add a customer reply or acknowledgement. Never include credentials or private payloads. |
| replace_launch_connectionB | After the owner securely uploads a fresh connection, verify repository ownership and replace the same already-authorized provider for a paid launch. Cannot retry uncertain writes or change submission plans. |
| get_orderA | Requires API key. Returns your owned order and bound launch after payment or timeout. Do not purchase again while outcome is unknown. |
| list_launchesC | Requires API key. Read durable execution and provider result states. |
| get_launchC | Requires API key. Read owned jobs, real provider IDs, evidence, ingestion waits and operator-attention states. Submitted is not approved; listed requires matching provider evidence. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| agent-guide |
TDQS
Scored across 32 tools
Several adjacent stages overlap, especially check_repository/import_repository/prepare_repository, check_launch_coverage/run_preflight/get_preflight, and create_server/create_launch/create_publisher_task. The descriptions are unusually detailed and often clarify non-goals, so an agent can usually disambiguate after reading, but the names alone are not enough.
Names are consistently snake_case, and most follow a verb_noun pattern such as list_servers, create_launch, and get_order. The main deviations are noun-phrase instruction tools like connection_instructions and payment_instructions, which are minor but keep it from being fully uniform.
With 32 tools, the surface is above the 25-tool heavy threshold and feels over-scoped for a single MCP server. The workflow is complex, but many stage-specific tools could likely be consolidated or grouped to reduce selection burden.
The set covers discovery, account management, repository preparation, preflight checks, launch/order/payment flows, publisher tasks, connections, and service cases. Minor gaps remain, such as no update/delete for server profiles, no launch cancellation, and no directory-detail retrieval, but the core lifecycle is well represented.