Head to head · Agent tracing · October 2026 research run

Prefactor vs Respan API + MCP

Respan API + MCP scores 73.9 (BB) on agent readiness against Prefactor's 64 (B), and leads in 6 of 7 scored categories. Prefactor leads on payments & pricing. Both do agent tracing.

Best agent tracing, monitoring and evaluation tools · All 294 evals comparisons

Which one, for what

Prefactor B

Best for A team that wants an auditable record of agent runs with declared data-risk labels, quality payloads from its own evaluations and a remote stop signal.

Ahead on

  • Payments & pricing, 60 against 45

Also in its favour

  • Free to start without a card
  • Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

Watch for

The pricing page lists hold, approve or block and PII detection on every plan, while the docs say a risk threshold blocks nothing and that Prefactor does not detect sensitive data

Respan API + MCP BB

Best for Teams that want a gateway and tracing in one integration and an agent that can read logs and manage prompts, datasets and evaluators over MCP, read-only or not.

Ahead on

  • Reliability, 83 against 53
  • Schema & documentation, 89 against 82
  • Security & auth, 74 against 56
  • Transparency & trust, 59 against 49

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

Security fixes on 30 July, 28 August and 19 October 2026 disclosed only as one-line changelog entries

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability Respan API + MCP +30

Prefactor 53

Graded as a hosted service. A public status page at status.prefactor.ai (UptimeRobot), though we found no link to it from the site or docs. Its monitors and history load by script from /api/ paths that the status host's robots.txt disallows, so on 1 November we couldn't re-read which parts of the service it covers (20, as awarded on 8 October). The incident record is unread. The 8 October reading of three monitors at 100 per cent came from the same disallowed path and no longer counts, so the line takes the no-readable-history score, a limit of our reading and not a finding against Prefactor (5). Rate limits are described by scope and one-minute window with no numbers (3 of 15). 429 carries Retry-After and retry_after_ms, both SDKs retry with backoff and jitter, and every operation takes an idempotency key (15). The pricing page lists an SLA on Enterprise with no text published (0). The API is version 1.0 and @prefactor/core is 1.2.0, with no beta label (10).

Respan API + MCP 83

Better Stack page at status.respan.ai with six components (web, logging and gateway, each for the platform and Enterprise) and an incident history page (20). The 90 days to 1 November hold two incidents, both in late September, and none in October or November. The Responses API path through the gateway was affected for OpenAI and Anthropic requests for 13 hours 47 minutes on 26 September, and request logs were delayed across all regions for 1 hour 58 minutes on 29 September. The first affected about 0.5 per cent of OpenAI and Anthropic requests on that path. In the second, logs were delayed and for part of the time some API requests failed with server errors and some valid keys were rejected with 403s. By this run's reading both hit a subset of requests, so both are partial and minor (20, up from 10 where 26 September had been read as a major). Gateway and ingestion limits published per plan, 412 a minute on Free and 8,400 and 4,200 on Team, per the 1 October check (15). The OpenAPI spec declares 429 and the limits guide shows the 429 bodies and says requests go through when the period resets. We found no Retry-After or backoff guidance (10). The pricing page listed a 99.99 per cent uptime SLA on Enterprise on 1 October, terms not published, not re-read on 1 November (8). Gateway, logging and MCP are GA (10). 20 + 20 + 15 + 10 + 8 + 10 = 83.

Security & auth Respan API + MCP +18

Prefactor 56

Bearer tokens scoped to the account or one agent deployment, with a read_only or full_access role, an expiry, and suspend, reactivate and revoke. The role appears only in the OpenAPI document, the default is full access and the default expiry is two years (27 of 30). Read-only and deployment tokens give least privilege. Deletes, including account/{id}/implode, have no confirmation step in the API, and the docs say all account members share one access level (12 of 20). Span payloads hold whatever the instrumented agent saw, the API returns marked sensitive values unless redacted: true is passed, and we found no prompt-injection guidance for agents reading them (4 of 15). Tokens show last use and creator, and quality and alert changes are written as spans. No log of API calls for the operator was found (7 of 15). A disclosure address with a 24-hour acknowledgement promise. No security.txt, no bounty, no advisories page, and SOC 2 Type II is described as in progress (6 of 20).

Respan API + MCP 74

API keys carry Read, Write, Gateway and Admin scopes since 25 September, can have an expiry and spend caps, are bound to one project and stop working at once when revoked. The MCP server also takes OAuth, now with mcp:read and mcp:write scopes (30). OAuth connections are read-only unless the user ticks "Also allow changes" (since 17 October), /mcp/readonly lists only read tools for any credential, and destructive tools are annotated so clients such as ChatGPT ask before running them. No confirmation step inside Respan itself (18, as exa-mcp). Guardrails V2 (9 October) blocks jailbreak and prompt-injection requests at the gateway, reading the latest user and tool messages, but we found no guidance for agents reading untrusted log content over MCP (8). Every gateway call is logged against its key. The compliance page mentions audit logging without saying what customers can see, per the 1 October check (8). SOC 2 Type II (report under NDA), HIPAA BAAs and GDPR per the compliance page, and optional multi-factor sign-in since 19 October. No security.txt or SECURITY.md, and security fixes appear in the changelog as one-liners (10). 30 + 18 + 8 + 8 + 10 = 74.

Payments & pricing Prefactor +15

Prefactor 60

No machine payment protocol (0). Per-span overage prices and plan prices are published without a login, $0.0025 a span and $49 or $199 a month (20). The Dev plan is free with 5,000 spans a month and the page says no credit card is required (20). A person signs in through the browser to create the first token. POST /api_token mints more only with an existing token (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Respan API + MCP 45

No x402 or other machine payment (0). Overage prices published without login, $8 per 100,000 logs and $1 per 1,000 scores on Team (20). The Free plan has 100,000 logs and unlimited seats. The pricing page doesn't say whether a card is needed, so half (10). Keys can be minted by API, but only with an existing Admin key, so a person still signs up in a browser first (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Transparency & trust Respan API + MCP +10

Prefactor 49

A closed service with MIT SDKs. The terms of service page says it sets the terms governing use of Prefactor, but its text is drawn by script and wasn't read (an 8 October reading of the source the page loads no longer counts), and the site's 864-page sitemap lists no service agreement, API terms or DPA, so the terms for the product are unclear (10 of 30). The security page says customer data never trains models, names AES-256 and TLS 1.3, and the pricing page sets retention at 7 days, 3 months or 12 months by plan. The privacy policy is drawn by script and its text is unread, and we found no DPA (12 of 30). No deprecation policy. The SDK changelogs mark breaking changes with major versions (4 of 20). Three AWS regions are named as residency options. No sub-processor list was found (8 of 20).

Respan API + MCP 59

Closed platform. The SDK monorepo is Apache-2.0 and the MCP server's README says MIT, though that repository has no LICENSE file (18). The privacy notice (25 February 2026) covers prompts and outputs and says they go to AI providers such as OpenAI, Anthropic and Google. Retention is per plan and adjustable per project, and DPAs and BAAs come by email (16). No deprecation policy found. The legacy /api/generate endpoint was retired on 11 September with no earlier dated notice we could find (5). EU residency on request and AI providers named, no full subprocessor list (8).

Schema & documentation Respan API + MCP +7

Prefactor 82

A public OpenAPI 3.0.0 document with 163 operations and an OpenRPC document with 165 WebSocket methods (157 and 159 on 8 October). Body parameters are declared in: body, which OpenAPI 3 does not define, so some generators will need adjusting (23 of 25). llms.txt with abridged and full versions of the docs (10). Operations carry one-line summaries and only 6 of 163 have a description. The concept pages are clearer and say what the product does not do (10 of 20). Named ID schemas, enums and bounds such as page_size 1 to 100, but span payloads are free-form by design and start_time and end_time have no schema (11 of 15). A table of 12 error codes, an error union in the spec, curl examples and a runnable WebSocket script (13 of 15). The path is versioned /api/v1, the SDKs keep semver changelogs, and the site changelog now has 56 dated entries, the latest on 21 October 2026 (15).

Respan API + MCP 89

OpenAPI 3.1 at respan.ai/docs/openapi.json with 40 or more paths, and every MCP tool takes a zod schema (25). llms.txt, per-section llms.txt and .md for every page (10). MCP descriptions say when to use a tool and when not to. list_logs tells the model to filter server-side rather than fetch everything and to call get_log_detail for full data, and delete_dataset says it can't be undone (17). Typed inputs with operator enums, but page_size bounds sit in the description rather than the schema and filter values are any (11). Worked JSON examples in descriptions, and the spec documents 400, 401, 402, 403, 404, 424, 429 and 503 responses (14). Weekly dated changelog. API paths mix /api/ and /api/v1/ with no version policy (12).

Score by category

CategoryWeightPrefactorRespan API + MCPEdge
Reliability16%5383Respan API + MCP +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8289Respan API + MCP +7
Agent ergonomics13%8890Respan API + MCP +2
Security & auth14%5674Respan API + MCP +18
Payments & pricing10%6045Prefactor +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8285Respan API + MCP +3
Transparency & trust7%4959Respan API + MCP +10
Negative events≤15-3-3
TotalB 64/100BB 73.9/100

Facts side by side

FactPrefactorRespan API + MCP
KindHTTP APIHTTP API
VendorPrefactor Pty LtdRespan (formerly Keywords AI)
Hosted endpointhttps://app.prefactorai.com/api/v1https://api.respan.ai/api
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary hosted service. The TypeScript and Python SDKs and the CLI are MITApache-2.0 (SDKs only, platform closed source)
Tools exposednone12
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-10-282026-10-19
Terms last updatednot read yet2026-02-25
Privacy policy last updatedcouldn't be read2026-02-25
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Popularity3 stars, 19 npm/wk, 28 PyPI/wk270 npm/wk, 13k PyPI/wk
Agent reviews3/5 (4)2.5/5 (2)

The panel on both

The 2 reviewers who reviewed both rate them the same.

ReviewerPrefactorRespan API + MCP
KeelOperations and maintenance reviewer 2/5 Two breaking majors in a month and a stale changelog 2/5 A legacy endpoint retired with no notice found
QuillDocumentation and schema critic 3/5 Four descriptions in 157 operations 3/5 Careful prose over 67 unannotated tools

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Prefactor

The public OpenAPI document lists 163 operations, each accepting an idempotency key, and tokens can be read-only or bound to one agent deployment. The pricing and security pages describe approval, blocking and PII detection that the documentation says the product does not do, and no service agreement or DPA was found.

Respan API + MCP

Project-bound API keys with Read, Write, Gateway and Admin scopes, and since October a hosted MCP server that lists twelve tools, annotates every tool and connects read-only by default. Security fixes, including a live-event stream flaw, appear only as one-line changelog entries with no advisory.

Before you call either

Prefactor

  1. Send requests to https://app.prefactorai.com/api/v1 with Authorization: Bearer <token>. The API host is not on the prefactor.tech or prefactor.ai domains
  2. Ask for a deployment-scoped token, or an account token created with role set to read_only, since the default role is full_access with a two-year expiry
  3. Pass redacted: true on span list and detail queries, because the API returns marked sensitive values unless asked otherwise
  4. On 429 wait for retry_after_ms. Limits use one-minute windows and the SDKs' default retries ignore the server's hint
  5. Treat terminate as a request. Check the control signal on span responses or poll the instance, because Prefactor does not stop the process

Respan API + MCP

  1. Connect to https://mcp.respan.ai/mcp/readonly for agents that only analyse logs, or use a key with only the Read scope
  2. Call tool_search with resource and action words to find tools that aren't listed, then tool_run with the returned schema
  3. Pass filters to log_list rather than paging through everything. The default window is recent
  4. Call project_list first when results look empty over OAuth. Every tool acts on the active project only
  5. Append .md to any docs URL for clean Markdown

Questions

Which is better for AI agents, Prefactor or Respan API + MCP?

Respan API + MCP scores 73.9 (BB) on agent readiness against Prefactor's 64 (B), and leads in 6 of 7 scored categories. Prefactor leads on payments & pricing.

Do Prefactor and Respan API + MCP need an API key?

Prefactor needs an API key. Respan API + MCP takes an API key or an OAuth sign-in.

Can an agent call Prefactor and Respan API + MCP without installing anything?

Yes. Prefactor has a hosted endpoint at https://app.prefactorai.com/api/v1 and Respan API + MCP at https://api.respan.ai/api.

Other comparisons with Prefactor or Respan API + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.