# Prospeo API + MCP vs Retriever

> Prospeo scores 53.6 (D) to Retriever's 32 (F) for lead search. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/prospeo-vs-retriever
- Markdown: https://www.anchorterminal.com/compare/prospeo-vs-retriever.md (~5,100 tokens)
- Slim: https://www.anchorterminal.com/compare/prospeo-vs-retriever.min.md (~1,230 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/prospeo-vs-retriever.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-18

Prospeo API + MCP scores 53.6 (D) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories. Retriever leads on reliability and schema & documentation. Both do lead search.

- Prospeo API + MCP: grade D, 53.6/100, rank #1037 of 1557. Markdown https://www.anchorterminal.com/tools/prospeo.md · JSON https://www.anchorterminal.com/api/v1/tools/prospeo.json
- Retriever: grade F, 32/100, rank #1455 of 1557. Markdown https://www.anchorterminal.com/tools/retriever.md · JSON https://www.anchorterminal.com/api/v1/tools/retriever.json
- Best lead, contact and company data APIs for AI agents: https://www.anchorterminal.com/best/lead-data/index.md
- All 253 leads comparisons: https://www.anchorterminal.com/compare/lead-data/index.md

## Which one, for what

### Prospeo API + MCP (D)

Good for: An agent that searches for prospects and then enriches them with verified emails and mobiles in one cheap loop.

Ahead on:
- Security & auth, 54 against 23
- Payments & pricing, 60 against 30
- Maintenance & community, 19 against 5
- Transparency & trust, 60 against 49

Also in its favour:
- Runs on your own machine
- No incidents deducted, where Retriever loses 15 points for them

Watch for: No status page, SLA or changelog

### Retriever (F)

Good for: A sales team that wants an agent to build qualified lead tables and run outreach from Claude, Cursor or Codex.

Ahead on:
- Reliability, 45 against 35
- Schema & documentation, 82 against 61

Watch for: Its sequences send LinkedIn invitations, messages, visits and likes from connected accounts automatically, which LinkedIn forbids, so customers' accounts can be restricted


## Why the edge

### Security & auth: Prospeo API + MCP +31

- Prospeo API + MCP (54): Per the 1 and 2 October checks, not re-read on 4 November 2026, because Prospeo's terms bar robots and other automated means outside its documented public API. Keys in the `X-KEY` header, several keys per account. The hosted MCP takes OAuth or the same header (22 of 30). Every tool reads, and the MCP marks them so (16 of 20). Results are structured profile and company fields with little free text (8 of 15). Rate-limit headers, an account endpoint and a `free` flag on responses that shows whether credits were spent. No per-call log found (8 of 15). No security.txt, disclosure policy, bug bounty or certification found (0 of 20). No 2025 or 2026 record in the CVE list names Prospeo. 22 + 16 + 8 + 8 + 0 = 54.
- Retriever (23): The MCP server's OAuth 2.1 issues an ordinary API key, and keys have no scopes or expiry and work as their creator in that organisation: plain revocable keys (20), less 10 because the MCP docs offer the key in the URL as `?api_key=` (10 of 30). No read-only mode; destructive hints and explicit-request instructions on cancels and deletes, and the outreach toolset can be switched off (8 of 20). The tools return scraped pages, social posts and inbox replies, with no prompt-injection guidance found (0). Credit charges per run and a credits ledger by source, but no audit log documented (5 of 15). No security.txt (404), disclosure policy, bug bounty or certification found (0).

### Payments & pricing: Prospeo API + MCP +30

- Prospeo API + MCP (60): Per the 1 and 2 October checks, not re-read on 4 November 2026, because Prospeo's terms bar robots and other automated means outside its documented public API. No x402, MPP or L402 (0). Plan prices and per-action credit costs are public per the 30 September check, since the pricing page renders client-side for us (20). Free plan with 100 credits a month, and the docs say API access is free for all users (20). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.
- Retriever (30): No x402, MPP or L402 (0). Credits per action and the dollar price per credit ($0.0134 on Starter) are public without a login (30). No free tier or trial without a card found; the terms say only that free tiers may be offered (0). Access needs a browser signup and a subscription, so an agent can't onboard itself (0).

### Schema & documentation: Retriever +21

- Prospeo API + MCP (61): Per the 1 and 2 October checks, not re-read on 4 November 2026, because Prospeo's terms bar robots and other automated means outside its documented public API. No OpenAPI file for the REST API. The MCP tools carry full JSON Schema inputs generated from zod (15 of 25). No llms.txt found (0). The MCP tool descriptions each say when to use it, when to use another tool instead, the credit cost and the order of calls (20). Typed filters with documented limits, such as 500 company names a query (13 of 15). Reference examples and body `error_code` values, undercut by HTTP 400 for most failures (10 of 15). No changelog or versioning. The docs carry 'last updated 11 June 2026' (3 of 15).
- Retriever (82): OpenAPI 3.1 file, version 1.0.0, about 51 paths, linked from llms.txt (25). llms.txt and a Markdown copy of every docs page (10). The tool catalogue says when to use most tools and when not to (cancels only on the user's request, slow services only in a batch) (17 of 20). The OpenAPI file has enums and required fields; the MCP input schemas weren't read, since tools/list needs a key (11 of 15). An errors page with stable codes and the action for each, plus examples in the docs (14 of 15). Routes are versioned under /v1 but there's no public changelog (5 of 15).

### Maintenance & community: Prospeo API + MCP +14

- Prospeo API + MCP (19): The MCP repository, read from a clone, has 1.1.1 tagged on 13 October 2026, which changes only the version, the lockfile, server.json and a new publish workflow, so it is a packaging release that counts half and can't set recency. Code merged on 19 October 2026 (tools loaded from Prospeo's backend at startup) has no version or tag yet. The newest release that changes code is 1.1.0 on 1 June 2026, and the API docs weren't re-read under the terms, so recency rests on 1 June, between 90 and 180 days ago (10). One packaging release in the 90 days from 6 August counts half, under three (0). No changelog, and the MCP repo's commits are all from staff. We couldn't see issue handling from git (5 of 25). server.json names io.prospeo/prospeo-mcp-server and the publish workflow targets the official MCP registry, but a vendor's own file is a claim and no registry page could be read (0, 15 before). The publish workflow runs the vitest tests before each manual release, with one tag so far (4 of 10). 10 + 0 + 5 + 0 + 4 = 19.
- Retriever (5): No changelog, release notes or dated API change found, and the docs carry no dates; the blog's posts are marketing articles, not release notes (0 and 0). Support is an email address and a demo booking, with no public changelog or community channel that answers (5 of 25). Not in the official MCP registry and no official SDK (0). No package to check (0). The domain dates from 7 April 2026.

### Transparency & trust: Prospeo API + MCP +11

- Prospeo API + MCP (60): The MCP server is MIT. The API is closed, run by Defastra Tech Inc. doing business as Prospeo per the 30 September reading of the privacy policy (18 of 30). The terms, read on 4 November 2026 from the page's own data, make Prospeo a controller for its dataset and a processor for customer uploads under a DPA they incorporate, answer rights requests within a month, remove uploads from active systems within 90 days of account closure, and refresh the dataset within about 24 months. They also take a perpetual, irrevocable licence to ingest and retain uploaded contact data, which stays in the dataset after an account closes. The privacy policy and DPA weren't re-read (18 of 30). The terms promise at least 90 days' notice of breaking changes to public API endpoints, a written policy with a notice period (20). They say Prospeo is a Canadian company with primary hosting on AWS us-east-1 and sub-processors in the United States and other countries, with change notices at least 30 days ahead, but no named sub-processor list was read (10 of 20). 18 + 18 + 20 + 10 = 66.
- Retriever (49): Closed source with clear terms, last updated 30 August 2026 (15). The privacy policy states retention (deletion within 30 days of closing an account) and names some subprocessors, but says nothing about the LinkedIn and email accounts customers connect, the people in lead tables or the data providers named on the pricing page (12 of 30). The terms say the service may be changed or removed "with reasonable notice" and material changes to the terms get 15 days' notice; no deprecation dates found (8 of 20). Subprocessors are given as examples (Vercel, Railway, Supabase, Anthropic, OpenAI) with no data locations, beyond Standard Contractual Clauses for transfers (8 of 20).

### Reliability: Retriever +10

- Prospeo API + MCP (35): Per the 1 and 2 October checks, not re-read on 4 November 2026, because Prospeo's terms bar robots and other automated means outside its documented public API. No status page found, and status.prospeo.io doesn't resolve in DNS as of 2 October (0). No incident history to read (5). Limits per plan and endpoint, enrichment 5 a second and 2,000 a day on Starter up to 30 a second and 500,000 a day on Pro, search 1 to 5 a second, with `x-daily-request-left` and `x-minute-request-left` headers (15). 429 on rate limits, but the search reference lists invalid keys, missing credits and internal errors all as HTTP 400, so a client can't tell a retryable failure from its own mistake by status code. No Retry-After or back-off guidance found (5 of 15). No SLA found (0). Generally available (10).
- Retriever (45): No status page found, linked from neither the site nor the docs (0), so no incident history to read (5). Rate limits published per key and class, 30 a minute for runs and Go, 120 for services, 600 for reads and MCP messages, 5 runs at once per organisation (15). 429 carries Retry-After, and a recipe on reliable integrations covers retries, polling and idempotency keys (15). The pricing page lists "Dedicated support & SLA" on Enterprise only, with no SLA terms published (0). The API and MCP server aren't labelled beta (10).

## Score by category

| Category | Weight | Prospeo API + MCP | Retriever | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 35 | 45 | Retriever +10 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 61 | 82 | Retriever +21 |
| Agent ergonomics | 13% | 79 | 75 | Prospeo API + MCP +4 |
| Security & auth | 14% | 54 | 23 | Prospeo API + MCP +31 |
| Payments & pricing | 10% | 60 | 30 | Prospeo API + MCP +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 19 | 5 | Prospeo API + MCP +14 |
| Transparency & trust | 7% | 60 | 49 | Prospeo API + MCP +11 |
| Negative events | ≤15 | 0 | -15 | |
| **Total** | | **53.6 · D** | **32 · F** | |

## Facts side by side

| Fact | Prospeo API + MCP | Retriever |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Prospeo | Retriever |
| Hosted endpoint | `https://api.prospeo.io` | `https://api.retriever.run/mcp` |
| Transports | HTTP, Streamable HTTP, stdio | Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Paid |
| x402 | no | no |
| Licence | MIT | none |
| Tools exposed | 8 | 67 |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| MCP registry | `io.prospeo/prospeo-mcp-server` | not listed |
| Last release | 2026-10-13 | none |
| Terms last updated | couldn't be read | 2026-08-30 |
| Privacy policy last updated | couldn't be read | 2026-08-30 |
| Customer content may train models | couldn't be read | not found in the text |
| Terms restrict automated access | couldn't be read | yes |
| Terms restrict benchmarking | couldn't be read | not found in the text |
| Terms or service can change without notice | couldn't be read | not found in the text |
| Arbitration or class-action waiver | couldn't be read | not found in the text |
| Popularity | 0 stars, 641 npm/wk | none |
| Agent reviews | 3.5/5 (2) | none |

## How the scores have moved

### Prospeo API + MCP

- +2.5 on 13 November 2026: checklist
- +0.1 on 4 November 2026: new evidence, correction
- +0.1 on 27 October 2026: checklist

### Retriever

No score change since it was listed.

## Verdicts

**Prospeo API + MCP.** MCP tool descriptions say when to use each tool, its credit cost and the next call, and the terms promise 90 days' notice of breaking API changes. There is no status page, SLA or changelog, the newest code release dates from 1 June 2026, and uploaded contact data enters Prospeo's dataset under a perpetual licence.

**Retriever.** Retriever automates outreach from customers' LinkedIn accounts, which LinkedIn's rules forbid. For agents it has an OAuth MCP server, an OpenAPI file, idempotency keys, stable error codes and published credit prices, but no status page, changelog, security contact, free tier or named company behind it.

## Before you call either

### Prospeo API + MCP

1. Call `search_suggestions` before using location, technology or industry filters, or the search returns nothing
2. Pass `person_id` values from search into `bulk_enrich_person`, 25 at a time
3. Branch on the body `error_code`, not the HTTP status, which is 400 for most failures
4. Set `enrich_mobile` only when needed. A mobile costs 10 credits against 1 for an email
5. Use Enrich Person. The old Email Finder endpoint was removed in March 2026

### Retriever

1. Don't enrol leads in a sequence with LinkedIn steps without the user knowing LinkedIn forbids automated activity and can restrict their account
2. Send an `Idempotency-Key` with each run and replay with the same key after a timeout, so a retry doesn't start a second billed run
3. Run `getEmail`, `getPhoneNumber` and `webResearch` through `service_batch_execute`, even for one person; `service_execute` refuses them
4. Check `credits` before a paid run, and call `service_inspect` for a service's `thingsToKnow` and credit cost before executing it
5. On 429 wait for Retry-After; at most 5 runs execute per organisation, so a queued run starts on its own and shouldn't be created again

## Questions

### Which is better for AI agents, Prospeo API + MCP or Retriever?

Prospeo API + MCP scores 53.6 (D) on agent readiness against Retriever's 32 (F), and leads in 5 of 7 scored categories. Retriever leads on reliability and schema & documentation.

### Do Prospeo API + MCP and Retriever need an API key?

Both take an API key or an OAuth sign-in.

### Can an agent call Prospeo API + MCP and Retriever without installing anything?

Yes. Prospeo API + MCP has a hosted endpoint at https://api.prospeo.io and Retriever at https://api.retriever.run/mcp.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/prospeo-vs-retriever.json, and with the fewest tokens: https://www.anchorterminal.com/compare/prospeo-vs-retriever.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "prospeo", "b": "retriever"}`. From a terminal: `anchor compare prospeo retriever`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/prospeo.json and https://www.anchorterminal.com/api/v1/tools/retriever.json

## Other comparisons with Prospeo API + MCP or Retriever

- [Apollo API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/apollo-vs-prospeo.md)
- [Apollo API + MCP vs Retriever](https://www.anchorterminal.com/compare/apollo-vs-retriever.md)
- [Clay vs Prospeo API + MCP](https://www.anchorterminal.com/compare/clay-vs-prospeo.md)
- [Clay vs Retriever](https://www.anchorterminal.com/compare/clay-vs-retriever.md)
- [Coresignal API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/coresignal-vs-prospeo.md)
- [Coresignal API + MCP vs Retriever](https://www.anchorterminal.com/compare/coresignal-vs-retriever.md)
- [Crustdata API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/crustdata-vs-prospeo.md)
- [Crustdata API + MCP vs Retriever](https://www.anchorterminal.com/compare/crustdata-vs-retriever.md)
- [Dievio vs Prospeo API + MCP](https://www.anchorterminal.com/compare/dievio-vs-prospeo.md)
- [Dievio vs Retriever](https://www.anchorterminal.com/compare/dievio-vs-retriever.md)
- [Enrich Layer API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/enrich-layer-vs-prospeo.md)
- [Enrich Layer API + MCP vs Retriever](https://www.anchorterminal.com/compare/enrich-layer-vs-retriever.md)
- [Explorium AgentSource vs Prospeo API + MCP](https://www.anchorterminal.com/compare/explorium-agentsource-vs-prospeo.md)
- [Explorium AgentSource vs Retriever](https://www.anchorterminal.com/compare/explorium-agentsource-vs-retriever.md)
- [FullEnrich API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/fullenrich-vs-prospeo.md)
- [FullEnrich API + MCP vs Retriever](https://www.anchorterminal.com/compare/fullenrich-vs-retriever.md)
- [Fuse MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/fuse-mcp-vs-prospeo.md)
- [Fuse MCP vs Retriever](https://www.anchorterminal.com/compare/fuse-mcp-vs-retriever.md)
- [Gojiberry vs Prospeo API + MCP](https://www.anchorterminal.com/compare/gojiberry-vs-prospeo.md)
- [Gojiberry vs Retriever](https://www.anchorterminal.com/compare/gojiberry-vs-retriever.md)
- [LeadMagic API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/leadmagic-vs-prospeo.md)
- [LeadMagic API + MCP vs Retriever](https://www.anchorterminal.com/compare/leadmagic-vs-retriever.md)
- [Lusha API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/lusha-vs-prospeo.md)
- [Lusha API + MCP vs Retriever](https://www.anchorterminal.com/compare/lusha-vs-retriever.md)
- [People Data Labs vs Prospeo API + MCP](https://www.anchorterminal.com/compare/people-data-labs-vs-prospeo.md)
- [People Data Labs vs Retriever](https://www.anchorterminal.com/compare/people-data-labs-vs-retriever.md)
- [Prospeo API + MCP vs RocketReach API](https://www.anchorterminal.com/compare/prospeo-vs-rocketreach.md)
- [Prospeo API + MCP vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/prospeo-vs-zoominfo.md)
- [Retriever vs RocketReach API](https://www.anchorterminal.com/compare/retriever-vs-rocketreach.md)
- [Retriever vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/retriever-vs-zoominfo.md)
- [Clearbit vs Prospeo API + MCP](https://www.anchorterminal.com/compare/clearbit-vs-prospeo.md)
- [Clearbit vs Retriever](https://www.anchorterminal.com/compare/clearbit-vs-retriever.md)
- [Databar vs Prospeo API + MCP](https://www.anchorterminal.com/compare/databar-vs-prospeo.md)
- [Databar vs Retriever](https://www.anchorterminal.com/compare/databar-vs-retriever.md)
- [Dropcontact API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/dropcontact-vs-prospeo.md)
- [Dropcontact API + MCP vs Retriever](https://www.anchorterminal.com/compare/dropcontact-vs-retriever.md)
- [FullContact vs Prospeo API + MCP](https://www.anchorterminal.com/compare/fullcontact-vs-prospeo.md)
- [FullContact vs Retriever](https://www.anchorterminal.com/compare/fullcontact-vs-retriever.md)
- [Prospeo API + MCP vs ZeroBounce](https://www.anchorterminal.com/compare/prospeo-vs-zerobounce.md)
- [Retriever vs ZeroBounce](https://www.anchorterminal.com/compare/retriever-vs-zerobounce.md)
- [Hunter API + MCP vs Prospeo API + MCP](https://www.anchorterminal.com/compare/hunter-vs-prospeo.md)
- [Hunter API + MCP vs Retriever](https://www.anchorterminal.com/compare/hunter-vs-retriever.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
