A MCP server for the Ankr Advanced API
Free
Nothing to run from here
Apicircle Cli 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
Command-line interface for API Circle Studio. Run mock servers, drive the MCP server, and import OpenAPI / Postman / Insomnia collections from any terminal.
Quickstart
# 1 — run it from where its publisher ships it
npx -y @apicircle/cli
# 2 — ask your agent something
> Command-line interface for API Circle Studio. Run mock servers, drive the MCP server, and import OpenAPI / Postman / Insomnia collections
Apicircle Cli is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
APAll 1 server
@apicircle1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
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 Apicircle Cli 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. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add apicircle-cli-mcp -- npx -y @apicircle/cliReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
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.
What you approve
69 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.
Create a new request from explicit fields and persist it.
Takes no parameters.
Example callreturns →
Read a request by id, or list summaries (id, name, method, url) when no id is provided.
Takes no parameters.
Example callreturns →
Patch fields on an existing request.
Takes no parameters.
Example callreturns →
Delete a request by id.
Takes no parameters.
Example callreturns →
Create a folder under an optional parent folder. Optionally seed folder-level
Takes no parameters.
Example callreturns →
Read a folder by id, or list all folders when no id is provided.
Takes no parameters.
Example callreturns →
Update a folder. Supply
Takes no parameters.
Example callreturns →
Delete a folder. Direct children (sub-folders + requests) are reparented to the deleted folder
Takes no parameters.
Example callreturns →
Create a new environment (or upsert one with the same name).
Takes no parameters.
Example callreturns →
Read environments — pass
Takes no parameters.
Example callreturns →
Replace the variables list of an environment.
Takes no parameters.
Example callreturns →
Delete an environment by name.
Takes no parameters.
Example callreturns →
Set (or clear) the active environment. Pass
Takes no parameters.
Example callreturns →
Replace the global environment priority order (highest priority first). Strings are interpreted as local env names. To target a linked env, pass
Takes no parameters.
Example callreturns →
Import an environment from the JSON shape produced by
Takes no parameters.
Example callreturns →
Create a new execution plan (sequence of request steps).
Takes no parameters.
Example callreturns →
Read a plan by id, or list all plans when no id is provided.
Takes no parameters.
Example callreturns →
Patch fields on an existing plan (name, steps, envPriorityOrder, stopOnAssertionFailure). Plan variables have their own tool (plan.set_variables).
Takes no parameters.
Example callreturns →
Delete a plan by id. Drops history rows referencing this plan.
Takes no parameters.
Example callreturns →
Append a step to an execution plan. Optional
Takes no parameters.
Example callreturns →
Remove a step from a plan by 0-based index.
Takes no parameters.
Example callreturns →
Replace the plan steps with a new permutation. The supplied indices must reference valid current step indices.
Takes no parameters.
Example callreturns →
Replace the plan-scoped variables. These live highest-priority during plan runs (above environment vars, below context vars).
Takes no parameters.
Example callreturns →
Run a plan headlessly (server-side). Currently returns a not-implemented marker — full execution requires the Desktop or browser runtime which the MCP host does not own. The Desktop integration overrides this tool with a real runner.
Takes no parameters.
Example callreturns →
Add an assertion to a request.
Takes no parameters.
Example callreturns →
List assertions for a request, or fetch a single assertion by id.
Takes no parameters.
Example callreturns →
Replace an existing assertion (matched by
Takes no parameters.
Example callreturns →
Remove an assertion from a request.
Takes no parameters.
Example callreturns →
Return the full
Takes no parameters.
Example callreturns →
Bulk-replace the workspace. Pass
Takes no parameters.
Example callreturns →
Create a new environment from an LLM-shaped JSON envelope. The model produces { name, variables: [{ key, value, encrypted }] }; this tool validates and persists it.
Takes no parameters.
Example callreturns →
Add an assertion to a request from an LLM-shaped JSON envelope. Useful when the user asks
Takes no parameters.
Example callreturns →
Create an execution plan from an LLM-shaped JSON envelope. The model produces { name, stepRequestIds: [...] } and the tool validates that each id exists in the workspace before persisting.
Takes no parameters.
Example callreturns →
Create a fully-shaped request from an LLM-shaped JSON envelope: method, url, headers, query params, body, auth, and inline assertions. The model produces a flat object; this tool generates the request id, normalizes auth (defaults to
Takes no parameters.
Example callreturns →
Patch an existing request from an LLM-shaped JSON envelope. Provided fields replace the existing values; omitted fields are left untouched. Arrays (headers, queryParams, assertions) are full replacements when supplied. Returns
Takes no parameters.
Example callreturns →
Create a recursive folder hierarchy from an LLM-shaped JSON envelope. The model produces
Takes no parameters.
Example callreturns →
Append one or more steps to an existing execution plan from an LLM-shaped JSON envelope. The model produces
Takes no parameters.
Example callreturns →
Replace the plan-scoped variables on an execution plan from an LLM-shaped JSON envelope. The model produces
Takes no parameters.
Example callreturns →
Declare an endpoint
Takes no parameters.
Example callreturns →
Scan source code for HTTP route definitions (Express, FastAPI, NestJS, Spring) and return candidate requests for the user to confirm before import.
Takes no parameters.
Example callreturns →
Generate runnable code (curl / JavaScript fetch / Node Axios / Python requests / Go net/http / Rust reqwest) that reproduces a workspace request.
Takes no parameters.
Example callreturns →
Export an existing folder (and its subtree) to the API Circle exchange JSON format.
Takes no parameters.
Example callreturns →
Import an
Takes no parameters.
Example callreturns →
Link a workspace by fetching its
Takes no parameters.
Example callreturns →
Re-pull a linked workspace
Takes no parameters.
Example callreturns →
Create a
Takes no parameters.
Example callreturns →
Search the API Circle marketplace for public workspaces tagged with
Takes no parameters.
Example callreturns →
Replace a repo
Takes no parameters.
Example callreturns →
Register a Global File Asset entry. Bytes are NOT carried — MCP returns the new asset id and the asset enters the
Takes no parameters.
Example callreturns →
Rename or re-describe a Global File Asset. Provenance refs (workingBranchRef, baseBranchRef) and binary metadata (slotId, sha256, size, mimeType) are preserved verbatim.
Takes no parameters.
Example callreturns →
Delete a Global File Asset. Cascades — every request body and mock-response body that referenced the asset is unbound in the same mutation. The result envelope includes the consumer list that was cleared so the caller can report what changed.
Takes no parameters.
Example callreturns →
List request-run history rows in reverse-chronological order. Filter by
Takes no parameters.
Example callreturns →
Fetch a single history row in full (headers, body preview, assertion results).
Takes no parameters.
Example callreturns →
Delete a single request-run row by id.
Takes no parameters.
Example callreturns →
Drop every request-run + plan-run older than
Takes no parameters.
Example callreturns →
Parse a
Takes no parameters.
Example callreturns →
Parse an OpenAPI / Swagger spec (YAML or JSON) and create one Request per operation. Returns the list of created request ids.
Takes no parameters.
Example callreturns →
Parse a Postman v2/v2.1 collection JSON and create one Request per item.
Takes no parameters.
Example callreturns →
Parse an Insomnia v4 export and create one Request per resource of type
Takes no parameters.
Example callreturns →
Parse an HTTP Archive (.har) JSON and create one Request per recorded entry. Cookies, response, and timings are dropped.
Takes no parameters.
Example callreturns →
List the workspaces this workspace links to (consumes). Each entry includes its source repo/branch, scope, pinned version, required secret-key ids, and the current version of its cached release ledger.
Takes no parameters.
Example callreturns →
Read one linked workspace by id, including its cached release ledger (the versions available to pin to).
Takes no parameters.
Example callreturns →
Update an existing linked workspace
Takes no parameters.
Example callreturns →
Unlink a workspace by id. Removes the link, its cached release ledger, every local override for it, the cached collections/environments snapshot, and any per-link session entry. The source repo is untouched.
Takes no parameters.
Example callreturns →
List this workspace
Takes no parameters.
Example callreturns →
Publish a new release of this workspace. Appends a semver version + markdown notes to the ledger and bumps currentVersion. The release is fingerprinted with a SHA-256 of the workspace at publish time. Rejects invalid semver or a duplicate version. Does NOT create a Git tag or GitHub Release.
Takes no parameters.
Example callreturns →
Mark a published version as deprecated (soft signal). Consumers see a warning but the version stays installable. Errors if the version is unknown or no ledger exists.
Takes no parameters.
Example callreturns →
Withdraw (yank) a published version (hard signal). Consumers are warned the version is broken / unsafe and told to move to a different one. The entry stays in the ledger. Errors if the version is unknown or no ledger exists.
Takes no parameters.
Example callreturns →
List every workspace registered with this server, including which one is currently active.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Apicircle Cli costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 99 / 100
Release 1.3.0 · scanned 26 Aug 2026
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.
Threat score100
Client score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest064f7f3b2a628bc29aba3efe0e683b5ccf7d10d9fbdfd16f4eae91529dde74aa
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
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.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest064f7f3b2a628bc2
Scanned2026-08-26
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
Pinned to 1.3.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.3.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Apicircle Cli in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
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 an account with 50 real tool calls against it.