Model Context Protocol (MCP) server for Apollo.io API integration
Nothing to run from here
OpenSDR 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.
97/100
trust score
17
tools declared
local
runs on your machine
—
downloads a day
What it does
Open-source AI SDR: B2B prospecting, email enrichment, buying signals and safe outreach staging.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user opensdr-mcp '--' npx -y opensdr-mcp
# 2 — ask your agent for something these tools do
# sdr_sync_hubspot, sdr_prepare_outreach_brief, sdr_create_campaign and 14 more
OpenSDR costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AJAll 2 servers
arif-js2 servers
2 categories
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 OpenSDR 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.
Claude Codedeclared by this listing
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. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user opensdr-mcp '--' npx -y opensdr-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take APOLLO_API_KEY (Apollo API key for people/company search and enrichment (optional)), HUNTER_API_KEY (Hunter API key for email finding and verification (optional)), EXA_API_KEY (Exa API key for buying signals and account research (optional)), TAVILY_API_KEY (Tavily API key, an alternative to Exa for signals and research (optional)), INSTANTLY_API_KEY (Instantly API v2 key for draft campaigns and lead enrollment (optional)), HUBSPOT_ACCESS_TOKEN (HubSpot private-app token for contact sync (optional)), OPENSDR_READ_ONLY (Set to 1 to disable every tool that writes to an external service), OPENSDR_MAX_CREDITS_PER_CALL (Hard cap on estimated paid provider credits per tool call), OPENSDR_DATA_DIR (Local data directory for lists, cache and suppression list (default ~/.opensdr)) if you want to set them.
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
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.
Upsert prospects into HubSpot as contacts (keyed by email), with an optional lifecycle stage and a note. Two-phase: call without confirm to preview, show the preview to the user, then call again with confirm=true and the confirmation_token after explicit approval. If any approved contact changes…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prospect_ids | array | no | — |
| list | string | no | — |
| lifecycle_stage | string | no | — |
| overwrite_existing | boolean | no | — |
| add_note | boolean | no | — |
| include_suppressed | boolean | no | — |
| confirm | boolean | no | — |
| confirmation_token | string | no | — |
Prepare a grounded outreach brief: seller context, per-prospect facts and top signals, a sequence framework and the rules for writing compliant copy. Free, local, read-only. It does NOT write the copy — you do. Save your drafts with sdr_save_prospects (custom_fields.first_line). Suppressed…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prospect_ids | array | yes | — |
| seller_context | string | no | — |
| touches | integer | no | — |
| channels | array | no | — |
| tone | string | no | — |
Create an Instantly campaign. OpenSDR never activates it: creation sends no activation flag, and the response reports the status Instantly returned (normally "draft"). Two-phase: call without confirm to get a preview and a confirmation_token, show the preview to the user, then call again with…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| steps | array | yes | — |
| schedule | object | yes | — |
| sending_accounts | array | no | — |
| confirm | boolean | no | — |
| confirmation_token | string | no | — |
Enroll prospects into an existing Instantly campaign. Only campaigns in "draft" or "paused" status are accepted, because adding leads to an active campaign starts sending. Two-phase: call without confirm to preview the campaign status and who is eligible/excluded (suppression, no email,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| campaign_id | string | yes | — |
| prospect_ids | array | no | — |
| list | string | no | — |
| allow_unverified | boolean | no | — |
| confirm | boolean | no | — |
| confirmation_token | string | no | — |
Find and verify a work email for people through a cost-aware waterfall: Apollo match -> Hunter finder -> optional Hunter verifier -> free local checks (syntax, MX, disposable, role). Paid tiers stop when the budget runs out. Returns each person with an email status, confidence, and a trail of…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| people | array | yes | People to enrich (1-25). |
| max_credits | integer | no | Per-call credit cap. |
| force_refresh | boolean | no | Bypass the cache. |
| verify_with_hunter | boolean | no | Run the Hunter verifier too. |
Enrich up to 10 company domains with firmographics (industry, headcount, location, technologies, funding) via Apollo organization enrichment. Consumes ~1 Apollo credit per domain; checks the per-call budget first and caches results. Use it after sdr_search_people to qualify accounts, or before…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domains | array | yes | Domains (1-10). |
| max_credits | integer | no | Per-call credit cap. |
| force_refresh | boolean | no | Bypass the cache. |
Check whether email addresses are deliverable. Always runs free local checks (syntax, MX, disposable domain, role address). With use_provider=true and a Hunter key, it also runs the Hunter verifier (1 credit each, cached). Returns a status (verified | likely | accept_all | unknown | invalid), a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| emails | array | yes | Emails to check (1-25). |
| use_provider | boolean | no | Also run the Hunter verifier. |
Show mode, configured providers, limits and credits used
No parameter schema on file.
Look up normalized titles, seniorities, sizes and industries (free, local)
No parameter schema on file.
Search people by title, seniority, company and location (Apollo)
No parameter schema on file.
Find accounts matching your ideal customer profile (Apollo)
No parameter schema on file.
Save people to local lists with dedupe and merge
No parameter schema on file.
Query saved prospects and lists
No parameter schema on file.
Export a list to a spreadsheet-safe CSV
No parameter schema on file.
Do-not-contact list for emails and domains
No parameter schema on file.
Funding, hiring, leadership and launch signals with sources (Tavily/Exa)
No parameter schema on file.
Gather cited sources about an account
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- 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 OpenSDR or to call it, 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: —
ATrust score 97 / 100
Release 1.0.1 · scanned 16 Oct 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 score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest0a35c858ed7719b57182199c101ef5b8845cd98cecb2824397e0c20870d8607c
Score vectorthreat 100 → client 97
| 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 |
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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
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>".
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| sdr_provider_status | no tags | |
| sdr_sync_hubspot | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sdr_prepare_outreach_brief | no tags | |
| sdr_create_campaign | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sdr_push_to_campaign | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sdr_waterfall_enrich_person | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sdr_enrich_company | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sdr_verify_email | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sdr_save_prospects | state-write | state-write: declares readOnlyHint: false |
| sdr_list_prospects | no tags | |
| sdr_export_csv | state-write | state-write: declares readOnlyHint: false |
| sdr_manage_suppression | state-write | state-write: declares readOnlyHint: false |
| sdr_lookup_filters | no tags | |
| sdr_search_people | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sdr_search_companies | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sdr_detect_buying_signals | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| sdr_research_account | external-sink | external-sink: declares readOnlyHint: false, 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest0a35c858ed7719b5
Scanned2026-10-16
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 1.0.1. Pin a release below and the command asks for exactly that one.
1.0.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish OpenSDR can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.