Salesforce
mcpotherio.github.WYRE-AI/salesforce-mcp · v1.0.6
MCP server for Salesforce CRM — Accounts, Contacts, Opportunities, Leads, Cases.
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
#!/usr/bin/env bash
# salesforce (io.github.WYRE-AI/salesforce-mcp), recipe docker (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-salesforce.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec docker run --rm --name mcp-my-agent-salesforce -p 127.0.0.1:${PORT}:8000 --env-file /etc/mcp/my-agent.env ghcr.io/wyre-ai/salesforce-mcp:v1.0.6
[Unit]
Description=MCP server salesforce (toolset my-agent), generated by Hub
After=network-online.target docker.service
Wants=network-online.target
[Service]
Type=simple
User=mcp
Group=mcp
SupplementaryGroups=docker
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/salesforce
WorkingDirectory=/var/lib/mcp/salesforce
ExecStart=/opt/mcp/my-agent/bin/salesforce.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/salesforce
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
docker run --rm -p 127.0.0.1:8101:8000 -e AUTH_MODE -e SALESFORCE_AUTH_FLOW -e SALESFORCE_CLIENT_ID -e SALESFORCE_CLIENT_SECRET -e SALESFORCE_INSTANCE_URL -e SALESFORCE_USERNAME -e SALESFORCE_PASSWORD -e SALESFORCE_TOKEN -e MCP_TRANSPORT -e LOG_LEVEL ghcr.io/wyre-ai/salesforce-mcp:v1.0.6
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T11:04:03+00:00).
# Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
# cp .env.example .env # fill the ${VAR}s
# docker compose up -d && bash smoke.sh
# Remote servers are not here: clients reach them directly (see clients/).
name: mcp-my-agent
services:
salesforce:
image: ghcr.io/wyre-ai/salesforce-mcp:v1.0.6
ports:
- 127.0.0.1:8101:8000
restart: unless-stopped
x-note: 'CHANGE_ME: check the image''s README for its transport and port; this assumes streamable
HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command
instead.'
environment:
AUTH_MODE: ${AUTH_MODE}
SALESFORCE_AUTH_FLOW: ${SALESFORCE_AUTH_FLOW}
SALESFORCE_CLIENT_ID: ${SALESFORCE_CLIENT_ID}
SALESFORCE_CLIENT_SECRET: ${SALESFORCE_CLIENT_SECRET}
SALESFORCE_INSTANCE_URL: ${SALESFORCE_INSTANCE_URL}
SALESFORCE_USERNAME: ${SALESFORCE_USERNAME}
SALESFORCE_PASSWORD: ${SALESFORCE_PASSWORD}
SALESFORCE_TOKEN: ${SALESFORCE_TOKEN}
MCP_TRANSPORT: ${MCP_TRANSPORT}
LOG_LEVEL: ${LOG_LEVEL}
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T11:04:03+00:00).
# kubectl create namespace mcp
# kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
# kubectl apply -f kubernetes.yaml
# Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
# with auth in front before exposing any of them.
apiVersion: v1
kind: Namespace
metadata:
name: mcp
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: salesforce
namespace: mcp
labels: &id001
app: salesforce
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: salesforce
image: ghcr.io/wyre-ai/salesforce-mcp:v1.0.6
ports:
- containerPort: 8000
name: http
env:
- name: AUTH_MODE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: AUTH_MODE
- name: SALESFORCE_AUTH_FLOW
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_AUTH_FLOW
- name: SALESFORCE_CLIENT_ID
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_CLIENT_ID
- name: SALESFORCE_CLIENT_SECRET
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_CLIENT_SECRET
- name: SALESFORCE_INSTANCE_URL
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_INSTANCE_URL
- name: SALESFORCE_USERNAME
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_USERNAME
- name: SALESFORCE_PASSWORD
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_PASSWORD
- name: SALESFORCE_TOKEN
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_TOKEN
- name: MCP_TRANSPORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MCP_TRANSPORT
- name: LOG_LEVEL
valueFrom:
secretKeyRef:
name: mcp-credentials
key: LOG_LEVEL
---
apiVersion: v1
kind: Service
metadata:
name: salesforce
namespace: mcp
spec:
selector:
app: salesforce
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T11:04:03+00:00).
# Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
# Each server under `servers` is one Deployment + Service; the keys after it configure
# upstream charts a worker verified.
servers:
salesforce:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: salesforce
image: ghcr.io/wyre-ai/salesforce-mcp:v1.0.6
ports:
- containerPort: 8000
name: http
env:
- name: AUTH_MODE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: AUTH_MODE
- name: SALESFORCE_AUTH_FLOW
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_AUTH_FLOW
- name: SALESFORCE_CLIENT_ID
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_CLIENT_ID
- name: SALESFORCE_CLIENT_SECRET
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_CLIENT_SECRET
- name: SALESFORCE_INSTANCE_URL
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_INSTANCE_URL
- name: SALESFORCE_USERNAME
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_USERNAME
- name: SALESFORCE_PASSWORD
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_PASSWORD
- name: SALESFORCE_TOKEN
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SALESFORCE_TOKEN
- name: MCP_TRANSPORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MCP_TRANSPORT
- name: LOG_LEVEL
valueFrom:
secretKeyRef:
name: mcp-credentials
key: LOG_LEVEL
# helm install my-agent helm/my-agent -n mcp
in the cloud
one click: the provider's deploy form opens filled in, in your own account- koyeb
-
The form opens with CHANGE_ME for each value you supply: AUTH_MODE, SALESFORCE_AUTH_FLOW, SALESFORCE_CLIENT_ID, SALESFORCE_CLIENT_SECRET, SALESFORCE_INSTANCE_URL, SALESFORCE_USERNAME, SALESFORCE_PASSWORD, SALESFORCE_TOKEN, MCP_TRANSPORT, LOG_LEVEL. Fill them in before you deploy.
Clients connect to the service's https://…koyeb.app address plus /mcp.
- azure
-
A Container Apps environment with one app per server, each with HTTPS ingress and one replica. The portal asks for each value you supply as a secure parameter; the deployment's outputs list the endpoints.
connect to it
copy what your client needsdocker run -i --rm -e AUTH_MODE -e SALESFORCE_AUTH_FLOW -e SALESFORCE_CLIENT_ID -e SALESFORCE_CLIENT_SECRET -e SALESFORCE_INSTANCE_URL -e SALESFORCE_USERNAME -e SALESFORCE_PASSWORD -e SALESFORCE_TOKEN -e MCP_TRANSPORT -e LOG_LEVEL ghcr.io/wyre-ai/salesforce-mcp:v1.0.6
{
"mcpServers": {
"salesforce": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"AUTH_MODE",
"-e",
"SALESFORCE_AUTH_FLOW",
"-e",
"SALESFORCE_CLIENT_ID",
"-e",
"SALESFORCE_CLIENT_SECRET",
"-e",
"SALESFORCE_INSTANCE_URL",
"-e",
"SALESFORCE_USERNAME",
"-e",
"SALESFORCE_PASSWORD",
"-e",
"SALESFORCE_TOKEN",
"-e",
"MCP_TRANSPORT",
"-e",
"LOG_LEVEL",
"ghcr.io/wyre-ai/salesforce-mcp:v1.0.6"
],
"env": {
"AUTH_MODE": "${AUTH_MODE}",
"SALESFORCE_AUTH_FLOW": "${SALESFORCE_AUTH_FLOW}",
"SALESFORCE_CLIENT_ID": "${SALESFORCE_CLIENT_ID}",
"SALESFORCE_CLIENT_SECRET": "${SALESFORCE_CLIENT_SECRET}",
"SALESFORCE_INSTANCE_URL": "${SALESFORCE_INSTANCE_URL}",
"SALESFORCE_USERNAME": "${SALESFORCE_USERNAME}",
"SALESFORCE_PASSWORD": "${SALESFORCE_PASSWORD}",
"SALESFORCE_TOKEN": "${SALESFORCE_TOKEN}",
"MCP_TRANSPORT": "${MCP_TRANSPORT}",
"LOG_LEVEL": "${LOG_LEVEL}"
}
}
}
}
#!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add salesforce -e "AUTH_MODE=${AUTH_MODE}" -e "SALESFORCE_AUTH_FLOW=${SALESFORCE_AUTH_FLOW}" -e "SALESFORCE_CLIENT_ID=${SALESFORCE_CLIENT_ID}" -e "SALESFORCE_CLIENT_SECRET=${SALESFORCE_CLIENT_SECRET}" -e "SALESFORCE_INSTANCE_URL=${SALESFORCE_INSTANCE_URL}" -e "SALESFORCE_USERNAME=${SALESFORCE_USERNAME}" -e "SALESFORCE_PASSWORD=${SALESFORCE_PASSWORD}" -e "SALESFORCE_TOKEN=${SALESFORCE_TOKEN}" -e "MCP_TRANSPORT=${MCP_TRANSPORT}" -e "LOG_LEVEL=${LOG_LEVEL}" -- docker run -i --rm -e AUTH_MODE -e SALESFORCE_AUTH_FLOW -e SALESFORCE_CLIENT_ID -e SALESFORCE_CLIENT_SECRET -e SALESFORCE_INSTANCE_URL -e SALESFORCE_USERNAME -e SALESFORCE_PASSWORD -e SALESFORCE_TOKEN -e MCP_TRANSPORT -e LOG_LEVEL ghcr.io/wyre-ai/salesforce-mcp:v1.0.6
{
"mcpServers": {
"salesforce": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"AUTH_MODE",
"-e",
"SALESFORCE_AUTH_FLOW",
"-e",
"SALESFORCE_CLIENT_ID",
"-e",
"SALESFORCE_CLIENT_SECRET",
"-e",
"SALESFORCE_INSTANCE_URL",
"-e",
"SALESFORCE_USERNAME",
"-e",
"SALESFORCE_PASSWORD",
"-e",
"SALESFORCE_TOKEN",
"-e",
"MCP_TRANSPORT",
"-e",
"LOG_LEVEL",
"ghcr.io/wyre-ai/salesforce-mcp:v1.0.6"
],
"env": {
"AUTH_MODE": "${AUTH_MODE}",
"SALESFORCE_AUTH_FLOW": "${SALESFORCE_AUTH_FLOW}",
"SALESFORCE_CLIENT_ID": "${SALESFORCE_CLIENT_ID}",
"SALESFORCE_CLIENT_SECRET": "${SALESFORCE_CLIENT_SECRET}",
"SALESFORCE_INSTANCE_URL": "${SALESFORCE_INSTANCE_URL}",
"SALESFORCE_USERNAME": "${SALESFORCE_USERNAME}",
"SALESFORCE_PASSWORD": "${SALESFORCE_PASSWORD}",
"SALESFORCE_TOKEN": "${SALESFORCE_TOKEN}",
"MCP_TRANSPORT": "${MCP_TRANSPORT}",
"LOG_LEVEL": "${LOG_LEVEL}"
}
}
}
}
{
"servers": {
"salesforce": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"AUTH_MODE",
"-e",
"SALESFORCE_AUTH_FLOW",
"-e",
"SALESFORCE_CLIENT_ID",
"-e",
"SALESFORCE_CLIENT_SECRET",
"-e",
"SALESFORCE_INSTANCE_URL",
"-e",
"SALESFORCE_USERNAME",
"-e",
"SALESFORCE_PASSWORD",
"-e",
"SALESFORCE_TOKEN",
"-e",
"MCP_TRANSPORT",
"-e",
"LOG_LEVEL",
"ghcr.io/wyre-ai/salesforce-mcp:v1.0.6"
],
"env": {
"AUTH_MODE": "${AUTH_MODE}",
"SALESFORCE_AUTH_FLOW": "${SALESFORCE_AUTH_FLOW}",
"SALESFORCE_CLIENT_ID": "${SALESFORCE_CLIENT_ID}",
"SALESFORCE_CLIENT_SECRET": "${SALESFORCE_CLIENT_SECRET}",
"SALESFORCE_INSTANCE_URL": "${SALESFORCE_INSTANCE_URL}",
"SALESFORCE_USERNAME": "${SALESFORCE_USERNAME}",
"SALESFORCE_PASSWORD": "${SALESFORCE_PASSWORD}",
"SALESFORCE_TOKEN": "${SALESFORCE_TOKEN}",
"MCP_TRANSPORT": "${MCP_TRANSPORT}",
"LOG_LEVEL": "${LOG_LEVEL}"
}
}
}
}
name: my-agent target: local servers: - hub: io.github.WYRE-AI/salesforce-mcp
- not probed yet: tools unpinned, ingest lists them
tools
Not probed yetThe tools appear once the hub or its worker has listed this entry. Running it still works: your client lists them on first start.