MCP server for per-agent cost attribution, budget management, and spend analytics across AI agent fleets
Free
Nothing to run from here
Force 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
A simple MCP server with packaged tools, for each Salesforce API (REST, Tooling, GraphQL, etc.)
Quickstart
# 1 — run it from where its publisher ships it
npx -y @rapidocloud/mcp-force
# 2 — ask your agent something
> A simple MCP server with packaged tools, for each Salesforce API (REST, Tooling, GraphQL, etc.)
Force is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
RAAll 1 server
@rapidocloud1 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 Force 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 force-mcp -- npx -y @rapidocloud/mcp-forceReconnect, 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
78 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.
Perform a tooling search in Salesforce.
Takes no parameters.
Example callreturns →
Run tests synchronously in Salesforce Tooling API.
Takes no parameters.
Example callreturns →
Run asynchronous tests in Salesforce Tooling API.
Takes no parameters.
Example callreturns →
Executes a query against an object using the Salesforce Tooling API.
Takes no parameters.
Example callreturns →
Execute Apex code anonymously on Salesforce.
Takes no parameters.
Example callreturns →
Retrieve available code completions for Apex system method symbols.
Takes no parameters.
Example callreturns →
Create a new Tooling SObject in Salesforce.
Takes no parameters.
Example callreturns →
Get tooling metadata for a specific Salesforce SObject.
Takes no parameters.
Example callreturns →
Lists the available Tooling API objects and their metadata.
Takes no parameters.
Example callreturns →
Get the tooling describe of a Salesforce SObject.
Takes no parameters.
Example callreturns →
Access records from Salesforce.
Takes no parameters.
Example callreturns →
Query Salesforce records using SOQL (Salesforce Object Query Language).
Takes no parameters.
Example callreturns →
Set, reset, or get information about a user password in Salesforce.
Takes no parameters.
Example callreturns →
Retrieve suggested Salesforce Knowledge articles for a specified SObject.
Takes no parameters.
Example callreturns →
Set, reset, or get information about a user password in Salesforce.
Takes no parameters.
Example callreturns →
Access Salesforce records based on the specified object ID.
Takes no parameters.
Example callreturns →
Delete a record from a specified Salesforce SObject.
Takes no parameters.
Example callreturns →
Creates or updates records in Salesforce based on external ID.
Takes no parameters.
Example callreturns →
Retrieve image data from a rich text area field in a Salesforce record.
Takes no parameters.
Example callreturns →
Access SObject relationships in Salesforce.
Takes no parameters.
Example callreturns →
Retrieve quick actions for a specific Salesforce SObject.
Takes no parameters.
Example callreturns →
Retrieve the PlatformAction SObject from Salesforce.
Takes no parameters.
Example callreturns →
Retrieve information about alternate named layouts for a given Salesforce object.
Takes no parameters.
Example callreturns →
Retrieve updated records for a specified Salesforce SObject.
Takes no parameters.
Example callreturns →
Retrieve deleted records for a specified Salesforce SObject.
Takes no parameters.
Example callreturns →
Describe the metadata for a specified Salesforce SObject.
Takes no parameters.
Example callreturns →
Create a new SObject in Salesforce.
Takes no parameters.
Example callreturns →
Retrieve compact layouts for a specific Salesforce object.
Takes no parameters.
Example callreturns →
Retrieve a specified blob field from an individual Salesforce record.
Takes no parameters.
Example callreturns →
Retrieve basic information about a specified Salesforce SObject.
Takes no parameters.
Example callreturns →
Retrieve approval layouts for a specified Salesforce object.
Takes no parameters.
Example callreturns →
Download a file from Salesforce.
Takes no parameters.
Example callreturns →
Describe SObject layouts in Salesforce.
Takes no parameters.
Example callreturns →
Describe SObject layouts per record type in Salesforce.
Takes no parameters.
Example callreturns →
Lists the available objects and their metadata for your organization’s data.
Takes no parameters.
Example callreturns →
Returns a list of layouts and descriptions for global objects.
Takes no parameters.
Example callreturns →
Retrieve compact layouts for specified Salesforce objects.
Takes no parameters.
Example callreturns →
Obtain an access token from Salesforce using the Web Server Flow.
Takes no parameters.
Example callreturns →
Initiate the OAuth 2.0 Web Server Flow for Salesforce.
Takes no parameters.
Example callreturns →
Authenticate using the Username Password Flow for Salesforce.
Takes no parameters.
Example callreturns →
Retrieve user information from Salesforce.
Takes no parameters.
Example callreturns →
Perform the User Agent Flow for Salesforce OAuth2 authentication.
Takes no parameters.
Example callreturns →
Perform a SOAP login to Salesforce.
Takes no parameters.
Example callreturns →
Retrieve Salesforce keys.
Takes no parameters.
Example callreturns →
Revoke an access token from Salesforce.
Takes no parameters.
Example callreturns →
Refresh the access token for Salesforce API.
Takes no parameters.
Example callreturns →
Introspects an OpenID Connect token with Salesforce.
Takes no parameters.
Example callreturns →
Register a new client using OpenID Connect Dynamic Client Registration Endpoint.
Takes no parameters.
Example callreturns →
Retrieve the OpenID Connect Discovery Endpoint from Salesforce.
Takes no parameters.
Example callreturns →
Obtain a JWT Bearer Token from Salesforce.
Takes no parameters.
Example callreturns →
Retrieve the ID token from Salesforce.
Takes no parameters.
Example callreturns →
Obtain an access token using Device Flow for Salesforce.
Takes no parameters.
Example callreturns →
Initiate the device flow for Salesforce OAuth2 authentication.
Takes no parameters.
Example callreturns →
Obtain an access token using the Client Credentials Flow.
Takes no parameters.
Example callreturns →
Obtain an access token using the Client Credentials Flow for Salesforce.
Takes no parameters.
Example callreturns →
Fetch the authentication configuration from Salesforce.
Takes no parameters.
Example callreturns →
Perform an Asset Token Flow to obtain a new access token from Salesforce.
Takes no parameters.
Example callreturns →
Refresh a sandbox in Salesforce.
Takes no parameters.
Example callreturns →
List all sandboxes in Salesforce.
Takes no parameters.
Example callreturns →
Retrieve a sandbox record from Salesforce.
Takes no parameters.
Example callreturns →
Get the status of a Salesforce sandbox.
Takes no parameters.
Example callreturns →
Delete a sandbox in Salesforce.
Takes no parameters.
Example callreturns →
Create or clone a sandbox in Salesforce.
Takes no parameters.
Example callreturns →
Fetch opportunities that are not closed from Salesforce.
Takes no parameters.
Example callreturns →
Fetch early stage opportunities from Salesforce.
Takes no parameters.
Example callreturns →
Fetch opportunities that are closing soon from Salesforce.
Takes no parameters.
Example callreturns →
Query opportunities closing soon in Salesforce.
Takes no parameters.
Example callreturns →
Fetch contacts from Salesforce using GraphQL.
Takes no parameters.
Example callreturns →
Fetch contacts along with their account names from Salesforce.
Takes no parameters.
Example callreturns →
Fetch ordered contacts from Salesforce using GraphQL.
Takes no parameters.
Example callreturns →
Query accounts from Salesforce using GraphQL.
Takes no parameters.
Example callreturns →
Query accounts with a filter using Salesforce GraphQL API.
Takes no parameters.
Example callreturns →
Fetch accounts with pagination from Salesforce GraphQL API.
Takes no parameters.
Example callreturns →
Retrieve an account by its ID from Salesforce.
Takes no parameters.
Example callreturns →
Update an account in Salesforce.
Takes no parameters.
Example callreturns →
Delete an account in Salesforce.
Takes no parameters.
Example callreturns →
Create an account in Salesforce.
Takes no parameters.
Example callreturns →
Perform an introspection query on Salesforce GraphQL API.
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. Force 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 93 / 100
Release 0.0.9 · 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 score93
Findings2 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest9ad3efcc3e55c20992f46f9d168e39700161ff6711967b2609aecd691a5ee50e
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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. high 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. | ||
can send data / act on an external service
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 digest9ad3efcc3e55c209
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 0.0.9 — 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.
0.0.9
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 Force 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.