Skip to main content
Glama
YawLabs

fetch-mcp

by YawLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

http_post

Destructive

Submit data to any HTTP endpoint using POST. Send raw string or JSON bodies, add headers or auth, and handle retries/timeouts for reliable webhook delivery and API resource creation.

Instructions

Perform an HTTP POST. Body can be given as a raw string (body) or as a JSON value (body_json — auto-sets content-type to application/json). NOT idempotent: calling twice submits twice.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesTarget URL (http:// or https://)
bodyNoRaw request body as a string
headersNoExtra request headers as a key/value object
retriesNoRetries on 408/425/429/500/502/503/504 with exponential backoff (default 0)
body_jsonNoRequest body as a JSON value — sets content-type to application/json if none given
max_bytesNoMax response body size in bytes before the body is truncated (default 5MiB, ceiling 100MiB)
basic_authNoHTTP Basic auth credentials
timeout_msNoTimeout in ms for each attempt, covering DNS, every redirect hop and the body (default 10000, max 120000). Retries get a fresh budget; a whole call is capped at 5 minutes.
user_agentNoUser-Agent override (default identifies as @yawlabs/fetch-mcp)
decode_textNoForce text decoding (true) or binary base64 (false). Defaults to auto — text for text/*, json, xml, etc; binary otherwise.
bearer_tokenNoBearer token sent as Authorization: Bearer <token>
content_typeNoContent-Type header to send with the body (e.g. application/json, text/plain, application/x-www-form-urlencoded)
max_redirectsNoMax redirect hops to follow (default 5)
allow_private_hostsNoAllow loopback / private / link-local targets for this call (default false). Refused unless the server operator launched fetch-mcp with FETCH_MCP_ALLOW_PRIVATE_HOSTS=1 -- SSRF protection stays on by default either way.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.0
    • changedInput schema / properties / allow_private_hosts / description
      Previous value: -"Allow requests to loopback / private / link-local addresses. SSRF protection is on by default — only flip this when intentionally talking to localhost."New value: +"Allow loopback / private / link-local targets for this call (default false). Refused unless the server operator launched fetch-mcp with FETCH_MCP_ALLOW_PRIVATE_HOSTS=1 -- SSRF protection stays on by default either way."
    • changedInput schema / properties / timeout_ms / description
      Previous value: -"Request timeout in ms (default 10000, max 120000)"New value: +"Timeout in ms for each attempt, covering DNS, every redirect hop and the body (default 10000, max 120000). Retries get a fresh budget; a whole call is capped at 5 minutes."
  2. First observedv0.6.1

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=true, so the safety profile is covered. The description reinforces this with 'NOT idempotent: calling twice submits twice,' which adds a concrete consequence, but it adds little beyond the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler; the core action, the key body-format choice, and the idempotency warning are all front-loaded and every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter tool this is concise, but the input schema is unusually thorough and the annotations carry the read/write and destructive profile. The description covers the main cross-parameter decision and the most important side-effect caveat; only explicit response/return behavior is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the schema already documents each parameter well. The description still adds value by framing body and body_json as the two mutually exclusive body-format options and highlighting that body_json auto-selects application/json.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear verb and resource: 'Perform an HTTP POST.' This unambiguously identifies the operation and, together with the tool name, separates it from the GET/PUT/PATCH/DELETE siblings. It lacks an explicit contrast with those siblings, so it stops just short of a top score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to choose POST over the sibling HTTP methods or the fetch_* helpers, and no exclusions or alternatives are mentioned. The non-idempotency warning is a behavioral caution, not a selection rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools