Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
Speedle is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
MCP server for self-hosted Speedle and Speedle Cloud: authorization checks and policy management
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'SPEEDLE_ENDPOINT=${SPEEDLE_ENDPOINT}' --env 'SPEEDLE_SERVICE_NAME=${SPEEDLE_SERVICE_NAME}' --transport stdio speedle-mcp '--' npx -y @speedle/mcp check
# 2 — ask your agent for something these tools do
# list_services, get_service, list_policies and 14 more
It needs SPEEDLE_ENDPOINT, SPEEDLE_SERVICE_NAME: this reads them from your environment, so export them first.
Speedle costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Speedle as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads SPEEDLE_ENDPOINT (ADS base URL, for example https://cloud.speedle.io or http://127.0.0.1:6734), SPEEDLE_SERVICE_NAME (Service name sent on every authorization check. Callers cannot override it) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx SPEEDLE_ENDPOINT …, setx SPEEDLE_SERVICE_NAME … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'SPEEDLE_ENDPOINT=${SPEEDLE_ENDPOINT}' --env 'SPEEDLE_SERVICE_NAME=${SPEEDLE_SERVICE_NAME}' --transport stdio speedle-mcp '--' npx -y @speedle/mcp checkReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs settings only you can give it: SPEEDLE_ENDPOINT — ADS base URL, for example https://cloud.speedle.io or http://127.0.0.1:6734.; SPEEDLE_SERVICE_NAME — Service name sent on every authorization check. Callers cannot override it.. You set them in your own client’s config, on your machine — this marketplace never holds it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List all Speedle services with their policies and role policies (GET /service). Read-only: this tool does not change any policy.
No parameter schema on file.
Get one Speedle service with its policies and role policies (GET /service/{serviceName}). Read-only: this tool does not change any policy.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
List the policies of a service, each with an SPDL rendering (GET /service/{serviceName}/policy). Read-only: this tool does not change any policy.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
Get one policy with an SPDL rendering (GET /service/{serviceName}/policy/{policyId}). Read-only: this tool does not change any policy.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
| policyId | string | yes | Policy ID. |
List the role policies of a service, each with an SPDL rendering (GET /service/{serviceName}/role-policy). Read-only: this tool does not change any policy.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
Get one role policy with an SPDL rendering (GET /service/{serviceName}/role-policy/{rolePolicyId}). Read-only: this tool does not change any policy.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
| rolePolicyId | string | yes | Role policy ID. |
Show every policy and role policy Speedle evaluates for a service, as SPDL: the service's own policies and role policies plus the role policies of the "global" service, which apply to every service. Built from GET /service/{serviceName} and GET /service/global (if the "global" service does not…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
Create a Speedle service (POST /service) and return the created service. On Speedle Cloud this returns 409 service_exists when the service already exists or the account has reached its service limit. This tool changes live authorization policies in the configured Speedle policy management service…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| type | string | no | Service type: "application" (default) or "k8s-cluster". |
Create a policy in a service from one SPDL statement or a structured body (POST /service/{serviceName}/policy) and return the created policy with its ID. This tool changes live authorization policies in the configured Speedle policy management service (a self-hosted PMS or Speedle Cloud).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
| name | string | yes | Human-readable policy name. |
| spdl | string | no | — |
| policy | object | no | Structured policy body (alternative to spdl). |
Create a role policy in a service from one SPDL statement or a structured body (POST /service/{serviceName}/role-policy) and return the created role policy with its ID. This tool changes live authorization policies in the configured Speedle policy management service (a self-hosted PMS or Speedle…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
| name | string | yes | Human-readable policy name. |
| spdl | string | no | — |
| rolePolicy | object | no | Structured role policy body (alternative to spdl). |
Delete a service and all of its policies and role policies (DELETE /service/{serviceName}). Destructive: "confirm" must equal serviceName, otherwise nothing is sent. Returns the deleted service as it was. This tool changes live authorization policies in the configured Speedle policy management…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
| confirm | string | yes | Must be exactly the serviceName being deleted. |
Delete one policy (DELETE /service/{serviceName}/policy/{policyId}). Destructive: "confirm" must equal policyId, otherwise nothing is sent. Returns the deleted policy as it was. This tool changes live authorization policies in the configured Speedle policy management service (a self-hosted PMS or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
| policyId | string | yes | Policy ID. |
| confirm | string | yes | Must be exactly the policyId being deleted. |
Delete one role policy (DELETE /service/{serviceName}/role-policy/{rolePolicyId}). Destructive: "confirm" must equal rolePolicyId, otherwise nothing is sent. Returns the deleted role policy as it was. This tool changes live authorization policies in the configured Speedle policy management service…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceName | string | yes | — |
| rolePolicyId | string | yes | Role policy ID. |
| confirm | string | yes | Must be exactly the rolePolicyId being deleted. |
Check whether a subject is allowed to perform an action on a resource in the configured Speedle service (/authz-check/v1/is-allowed). This tool only answers authorization questions and does not enforce anything or modify policies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject | yes | Subject to evaluate: a user name string or a non-empty list of principals. | |
| resource | string | yes | Resource identifier (for example "/books/123"). |
| action | string | yes | Action name (for example "get" or "write"). |
| attributes | no | — |
Diagnose why a subject is allowed or denied an action on a resource in the configured Speedle service (/authz-check/v1/diagnose), returning matched policies, role policies, granted roles, and condition evaluations. This tool only answers authorization questions and does not enforce anything or…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject | yes | Subject to evaluate: a user name string or a non-empty list of principals. | |
| resource | string | yes | Resource identifier (for example "/books/123"). |
| action | string | yes | Action name (for example "get" or "write"). |
| attributes | no | — |
List all roles granted to a subject in the configured Speedle service (/authz-check/v1/all-granted-roles). This tool only answers authorization questions and does not enforce anything or modify policies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject | yes | Subject to evaluate: a user name string or a non-empty list of principals. | |
| resource | string | no | Optional resource context for role evaluation. |
| action | string | no | Optional action context for role evaluation. |
| attributes | no | — |
List all permissions (resource and actions) granted to a subject in the configured Speedle service (/authz-check/v1/all-granted-permissions). This tool only answers authorization questions and does not enforce anything or modify policies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subject | yes | Subject to evaluate: a user name string or a non-empty list of principals. | |
| resource | string | no | Optional resource context for permission evaluation. |
| action | string | no | Optional action context for permission evaluation. |
| attributes | no | — |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under UPL-1.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Speedle or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (17 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 17 recovered tools are registered only when options.exposeDiagnose === true holds (dist/check/server.js:124) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 8.
1 of the 17 recovered tools are registered only when options.exposeAllGrantedRoles === true holds (dist/check/server.js:146) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 8.
1 of the 17 recovered tools are registered only when options.exposeAllGrantedPermissions === true holds (dist/check/server.js:172) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 8.
6 of the 17 recovered tools are registered only when options.readOnly is false (dist/manage/server.js:294) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 8.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
8 tools are registered unconditionally · (1) 1 more only when options.exposeDiagnose === true holds (dist/check/server.js:124) · (2) 1 more only when options.exposeAllGrantedRoles === true holds (dist/check/server.js:146) · (3) 1 more only when options.exposeAllGrantedPermissions === true holds (dist/check/server.js:172) · (4) 6 more only when options.readOnly is false (dist/manage/server.js:294) — typically when a key or option is configured. All 17 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| is_allowed | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| diagnose conditional (1) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| all_granted_roles conditional (2) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| all_granted_permissions conditional (3) | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_services | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_service | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_policies | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_policy | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_role_policies | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_role_policy | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| show_effective_policies | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| create_service conditional (4) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_policy conditional (4) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_role_policy conditional (4) | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| delete_service conditional (4) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| delete_policy conditional (4) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| delete_role_policy conditional (4) | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.9.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Speedle can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.