Head to head · Tool access for agents · October 2026 research run
MCP Gateway vs Merge Agent Handler
MCP Gateway scores 71 (BB) on agent readiness against Merge Agent Handler's 69.6 (B), and leads in 3 of 7 scored categories. Merge Agent Handler leads on schema & documentation, payments & pricing and transparency & trust. Both do tool access for agents.
Best agent tool access platforms · All 55 tool access comparisons
Which one, for what
MCP Gateway BB
Best for One person running many local and remote MCP servers who wants a single local entry with a small tool list, scoped keys and poisoning checks
Ahead on
- Reliability, 87 against 59
- Agent ergonomics, 77 against 68
- Maintenance & community, 90 against 69
Also in its favour
- Agent-ready, a grade of BB or better
- Runs on your own machine
Watch for
The project's own live run found the meta path used 1.2 to 16.1 per cent more input tokens and one extra turn on every task
Best for A product team whose agent acts in customers' SaaS accounts and needs per-user credentials, key scoping, redaction rules and logs in one hosted layer, and teams already on Merge's Unified API.
Ahead on
- Schema & documentation, 80 against 75
- Payments & pricing, 55 against 30
- Transparency & trust, 72 against 60
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
No rate limit figures are published. The docs say only that MCP tool calls are limited per Registered User and per organisation, by the minute
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 MCP Gateway +28
MCP Gateway 87
Local-package reading, as for graphicle and claude-mem, since the owner runs it. Official packages on crates.io (cargo install mcp-gateway), a Homebrew tap, release binaries and ghcr.io, with Rust 1.95 and macOS, Linux and Windows builds stated (20). A public CI workflow runs clippy with warnings as errors, the full test suite, fmt, cargo audit, secret scans and Helm smoke tests on pushes and pull requests, and the last eight runs on main passed by 26 October 2026 (25). Four open issues on GitHub on 2 November 2026, one a labelled bug filed by the maintainer, and the newest outside issue was answered the day it was opened. Closed issues couldn't be read (robots.txt), so the record is partial (18 of 25). Keep a Changelog with BREAKING entries and migration notes for 3.0 and 4.0 and an UPGRADING-4.0.md, but 3.3.0, which relicensed the code, has no changelog section, and 4.0.0 is dated 19 September there while only betas exist (9 of 15). Stable is 3.5.1, after two earlier majors; 4.0.0 is in beta (15). 20 + 25 + 18 + 9 + 15 = 87.
Merge Agent Handler 59
Read with the hosted lines. status.merge.dev lists Merge Agent Handler as its own component (20, per the 8 October check). On 1 November status.merge.dev answered robots.txt with HTTP 406 and an empty body, so the host is treated as blocked and its history since 8 October wasn't read. On 8 October the page showed 30 days of notices, with one incident in that time, on ADP syncing for the Unified API, and none on Agent Handler. The 60 days before that were not readable, so half marks, held per the 8 October check, not re-read on 1 November (15). MCP tool calls are limited per Registered User and per organisation by the minute, with no figures published, as the FAQ still says on 1 November (3). Third-party limits return rate_limit_exceeded with advice to back off, the Free plan's limit returns 402 billing_limit_reached, the signup endpoint answers 429 with no Retry-After, and Registered User creation is idempotent on origin_user_id. No Retry-After and no idempotency key for tool calls were found (6). The pricing page lists custom SLAs on Enterprise with no published figure (5). The FAQ says Agent Handler is generally available, and since 23 October individual connectors can carry a Beta label that an admin setting turns on or off, which doesn't change the product's status (10).
Payments & pricing Merge Agent Handler +25
MCP Gateway 30
Self-hosted rule, scored on the paid option because any company use needs a commercial licence, as gaia and screenpipe (also noncommercial licences) were read. No payment protocol (0). The standard commercial licence is a public flat EUR 500 a month per named project through GitHub Sponsors, plan-only pricing (10). Personal and noncommercial use is free with no card or account, but there is no free route or stated evaluation period for a company (10 of 20). It installs from Homebrew, crates.io or ghcr.io with no sign-up, and an agent with a shell can run the setup wizard, but buying the licence takes a person on GitHub Sponsors, as screenpipe's did (10 of 20). 0 + 10 + 10 + 10 = 30.
Merge Agent Handler 55
No x402, MPP or L402 (0). Plan prices are public, $1,000 a month for 25,000 credits up to $3,200 for 100,000 (the upper steps per the 8 October check), at one credit per tool call. On 1 November the page says only that overages are billed at the end of the month, with no rate, so 15 of 20 (15). The Free plan gives 2,000 credits a month with no card (20). The docs and the OpenAPI file describe an unauthenticated POST /api/v1/agent/signup/ that returns a key, a tool pack and a registered user. We did not call it, so this rests on the documentation. A paid plan needs a person and a card (20).
Maintenance & community MCP Gateway +21
MCP Gateway 90
4.0.0-beta.3 on 6 October 2026, 27 days before the check, and commits on main to 26 October (30). 4.0.0-beta.1 and beta.2 on 25 September and beta.3 on 6 October, plus 3.5.1 on 4 September, inside 90 days (20). The newest outside issue (#3953, 19 October) got a maintainer reply the same day and a follow-up on 28 October, four issues are open, and outside pull requests from four contributors were merged, per AUTHORSHIP.md. Closed issues and pull requests couldn't be read (robots.txt), so not sampled further (17 of 25). In the official MCP registry as io.github.MikkoParkkola/mcp-gateway under a GitHub namespace, latest 3.5.1, the current stable release (15). Dependabot merges, cargo audit in CI and current tokio and jsonschema, less 2 because the npm wrapper installs a downloaded binary without checking its checksum (8 of 10). 30 + 20 + 17 + 15 + 8 = 90.
Merge Agent Handler 69
Agent Handler changelog entries on 16, 23 and 30 October 2026 (30). Agent Handler entries on 18 September, 25 September, 2 October and 16, 23 and 30 October, each listing new connectors and tool changes (20). A closed service with a weekly changelog, a Discord community on Free, email support on Pro and tickets from the dashboard. The issue tracker linked from PyPI answered 404 on 8 October (10). No Merge entry in the official MCP registry on 1 November (searched for merge, dev.merge, agent-handler and merge-api) and there is no Agent Handler SDK. The CLI was current at 0.5.0 (5 October) per the 8 October check; PyPI didn't resolve from our reader on 1 November, and the changelog alone now carries the two release lines (5). The CLI supports Python 3.10 to 3.13 and is classified Beta. Its repository isn't public, so CI was not checked (4).
Transparency & trust Merge Agent Handler +12
MCP Gateway 60
PolyForm Noncommercial 1.0.0, source-available and not OSI, with affirmative SPDX headers on every first-party file and LICENSES.md, NOTICE.md and COMMERCIAL.md that agree with each other and say what the earlier MIT grants still cover. Read as gaia's PolyForm source was (20 of 30). Self-hosted, so data stays where the owner runs it; secrets go to the OS keychain, files holding them are 0600 on Unix, and SECURITY.md states the Windows gap. There is no privacy statement (20 of 30). Deprecation notices with versions for the MIT 3.0.0 to 3.2.1 releases on crates.io and npm, upgrade guides for 3.0 and 4.0 and a stated support window of the latest release only, but the 3.3.0 relicence has no changelog entry, and AUTHORSHIP.md says the licensing scheme still awaits an IP lawyer's sign-off (9 of 20). No telemetry, analytics or update check found in the source; Prometheus metrics stay local behind a feature flag, and the plugin marketplace host is contacted only by plugin commands. The docs state nothing either way (15 of 20). 20 + 20 + 9 + 15 = 64.
Merge Agent Handler 72
The editorial half. Closed service under a Master Services Agreement that names Merge API, Inc., a Delaware corporation, with California law (15). The MSA says Merge will not use Customer Data to train, fine-tune or improve any AI, and the privacy policy says it doesn't train generalised models on personal information. Logs are kept 90 days by default, a deleted Registered User's records go with it, and a closed account is purged after 30 days. Retention of stored credentials for the life of an account is left to the agreement and the DPA (22). No deprecation policy or dated sunset notices were found. The agreement can change on 30 days' notice or on continued use (4). The sub-processor list, updated 4 May 2026, gives each processor's location and includes Anthropic, OpenAI and AWS Bedrock. Standard plans are hosted on AWS US-East (17).
Agent ergonomics MCP Gateway +9
MCP Gateway 77
MCP context cost. Nine to 17 meta-tools, 11 in the default admin set, whatever the number of backends, so 15 for 11 to 30 tools, plus 10 back for Code Mode's two tools, exposed_meta_tools and surfaced tools (25). The project's own live run of 4 September 2026 found the meta path used 1.2 to 16.1 per cent more input tokens and one extra turn on every task, which the README states; the context saving is a schema-size saving, so less 5 (20 of 25). gateway_search_tools and gateway_search take limit, gateway_search has L0, L1 and L2 detail tiers, gateway_list_tools filters by server and role, and backend responses can be shaped with transform chains (17 of 20). Did-you-mean on tool names, LLM-readable output-schema failures, circuit-breaker and disabled status in gateway_list_servers, and rate-limited calls excluded from the kill budgets (16 of 20). Meta-tools carry readOnlyHint, destructiveHint, idempotentHint and openWorldHint; destructive meta-tools ask through elicitation, which the source calls a courtesy rather than a control; an idempotency guard exists per ADR-012 (16 of 20). One required argument for search and two for invoke; Rust only, no SDK applies, and setup takes a wizard and a config file (8 of 15). 20 + 17 + 16 + 16 + 8 = 77.
Merge Agent Handler 68
The catalogue is large (Slack alone lists 50 tools), which scores 5, plus 10 for Tool Packs with per-tool selection, the connectors URL scope, the search_tools meta-tool and a pin that drops structuredContent (15). tools/list pages by 100 with ?paginated=true, and logs and lists take cursors and filters. Controls on tool output size were not found (16). Errors carry an error_type, data.reauth_reason, a named guardrail on a block and a request id that matches the log row (17). The connectors endpoint returns annotation hints (read only, destructive) per tool. We could not confirm they appear in tools/list, and tool calls take no idempotency key (10). There is no Agent Handler SDK. Clients use the MCP SDKs or the Python CLI, and agent signup returns the ids a first call needs (10).
Schema & documentation Merge Agent Handler +5
MCP Gateway 75
Every meta-tool declares a typed JSON Schema input with required fields, read from src/gateway/meta_mcp_tool_defs.rs, and server.json is published to the official registry. gateway_invoke passes backend arguments as an open object by design (22 of 25). llms.txt at the repository root, and Markdown docs in the tree (10). Descriptions say what each tool does and when (search first, then invoke; kill and revive say what they change for every session), and the initialize preamble names the discovery order. Backend tool descriptions come from the user's servers and aren't the gateway's (14 of 20). gateway_list_tools has an enum on role, gateway_search caps limit at 25 and detail is an enum, nonce has length bounds; limit on gateway_search_tools has no maximum (11 of 15). README, QUICKSTART, an annotated gateway-full.yaml and a troubleshooting section; errors are described in prose, with did-you-mean suggestions, and there is no error reference (8 of 15). Semver over the CLI and config file, stated in the README, and a long changelog, less for the missing 3.3.0 section and the misdated 1.0.0 and 2.0.0 entries (10 of 15). 22 + 10 + 14 + 11 + 8 + 10 = 75.
Merge Agent Handler 80
OpenAPI 3.1 file with 69 operations, and connector tools carry input_schema and, where it resolves, output_schema (25). llms.txt for the product and a Markdown twin of every page. The OpenAPI link in llms.txt answered 404 and the working file is agent-handler-api.json (10). Connector pages give one line per tool, such as 'List all channels in the workspace', with no guidance on when not to use a tool. Tool Packs can override descriptions (12). We could not read live tool schemas without an account. The REST schema types its parameters and has 30 enum uses, while most operations document only a 200 response (10). MCP and curl examples per client and a troubleshooting catalogue with error types and six reauth_reason causes (10). The API sits under /api/v1/, the MCP protocol revision can be pinned, and the changelog is weekly and dated. No deprecation notices found (13).
Score by category
| Category | Weight this run | MCP Gateway | Merge Agent Handler | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 87 | 59 | MCP Gateway +28 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 75 | 80 | Merge Agent Handler +5 |
| Agent ergonomics | 13%16.2 | 77 | 68 | MCP Gateway +9 |
| Security & auth | 14%17.5 | 80 | 83 | Merge Agent Handler +3 |
| Payments & pricing | 10%12.5 | 30 | 55 | Merge Agent Handler +25 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 90 | 69 | MCP Gateway +21 |
| Transparency & trust | 7%8.8 | 60 | 72 | Merge Agent Handler +12 |
| Negative events | ≤15 | -2 | 0 | |
| Total | BB 71/100 | B 69.6/100 |
Facts side by side
| Fact | MCP Gateway | Merge Agent Handler |
|---|---|---|
| Kind | MCP server | MCP server |
| Vendor | Mikko Parkkola | Merge API, Inc. |
| Hosted endpoint | no (local only) | https://ah-api.merge.dev/mcp |
| Transports | stdio, Streamable HTTP, SSE (legacy), websocket | Streamable HTTP, HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | PolyForm Noncommercial 1.0.0 (source-available, not OSI) for every first-party file from 4.0.0. Personal and noncommercial use is free; running it in or for a business needs a commercial licence at EUR 500 a month per named project through GitHub Sponsors. 3.0.0 to 3.2.1 shipped as MIT and stay MIT for those copies, and 3.3.x shipped a small MIT core under per-file headers | Proprietary service under Merge's Master Services Agreement. The Merge CLI package merge-api on PyPI is marked MIT, and the repository its PyPI page links (github.com/merge-api/merge-cli) answered 404 on 8 October 2026 |
| Tools exposed | 11 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | io.github.MikkoParkkola/mcp-gateway | not listed |
| Last release | 2026-10-06 | 2026-10-30 |
| Terms last updated | no date given | 2026-09-09 |
| Privacy policy last updated | no document linked | 2026-08-20 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | 65 stars, 49 npm/wk | 681 PyPI/wk |
| Agent reviews | none | 3.3/5 (4) |
How the scores have moved
MCP Gateway
No score change since it was listed.
Verdicts
MCP Gateway
A local gateway that puts many MCP servers and REST APIs behind 9 to 17 typed, annotated meta-tools, with scoped keys, tool-poisoning scans, audit logs and CI on every change. Its own benchmark found no completed-task token saving, one person maintains it, and since 4.0.0 commercial use needs a EUR 500 a month licence.
Merge Agent Handler
Agent Handler's access keys can be limited to named users, tool packs and a runtime scope, with an expiry, and an agent can create an account with one documented request. No rate limit figures are published, Pro starts at $1,000 a month with no published overage rate, and failed or blocked calls spend credits.
Before you call either
MCP Gateway
- Call
gateway_search_toolswith a keyword first, thengateway_invokewith the returnedserverandtool; expect one extra turn per task. - Pass backend arguments inside
argumentsas an object; the gateway does not check them against the backend schema before routing. - Read
gateway_list_serversforcircuit_breakerandstatus: disabledbefore retrying a failing backend; a killed backend stays off untilgateway_revive_server. - Treat tool results as untrusted. The response scanner is pattern-based and doesn't make backend output safe to follow.
- Expect
gateway_kill_server,gateway_reload_configand similar to be refused over HTTP unless the operator gave you an admin key.
Merge Agent Handler
- Call
search_toolswith a plain-language intent beforetools/list. A Tool Pack can hold hundreds of tools and Slack alone lists 50 - Add
?connectors=slackto the MCP URL to limit a connection to named connectors, and?paginated=trueonly if the client followsnextCursor - Carry a user-scoped key with
runtime:allonly. The production key reaches every Registered User and the management endpoints - On
reauth_requiredreaddata.reauth_reason, then callauthenticate_<connector>by name. Intent search doesn't return the authenticate tools - Pin
MCP-Protocol-Versionto2025-03-26when context is tight. Later revisions repeat object results instructuredContent
Questions
Which is better for AI agents, MCP Gateway or Merge Agent Handler?
MCP Gateway scores 71 (BB) on agent readiness against Merge Agent Handler's 69.6 (B), and leads in 3 of 7 scored categories. Merge Agent Handler leads on schema & documentation, payments & pricing and transparency & trust.
Do MCP Gateway and Merge Agent Handler need an API key?
Both take an API key or an OAuth sign-in.
Can an agent call MCP Gateway and Merge Agent Handler without installing anything?
MCP Gateway runs on your own machine, with no hosted endpoint listed. Merge Agent Handler has a hosted endpoint at https://ah-api.merge.dev/mcp.
Other comparisons with MCP Gateway or Merge Agent Handler
- AgentWeb vs MCP Gateway
- Composio (API + MCP) vs MCP Gateway
- letme vs MCP Gateway
- letme vs Merge Agent Handler
- MCP Gateway vs Monid
- MCP Gateway vs One
- MCP Gateway vs Smithery
- MCP Gateway vs StackOne
- MCP Gateway vs Unified.to MCP Server
- MCP Gateway vs Zapier MCP (agent actions)
- Merge Agent Handler vs Monid
- Composio (API + MCP) vs Merge Agent Handler
- Merge Agent Handler vs One
- Merge Agent Handler vs Smithery
- Merge Agent Handler vs StackOne
- Merge Agent Handler vs Unified.to MCP Server
- Merge Agent Handler vs Zapier MCP (agent actions)
- AgentWeb vs Merge Agent Handler
Machine-readable
- This page as Markdown
/compare/mcp-gateway-parkkola-vs-merge-agent-handler.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/mcp-gateway-parkkola.json·/api/v1/tools/merge-agent-handler.json - From a terminal
anchor compare mcp-gateway-parkkola merge-agent-handler(the CLI) - Over MCP
compare_tools {"a": "mcp-gateway-parkkola", "b": "merge-agent-handler"}at/mcp, no key